rfc9845.original   rfc9845.txt 
Network Working Group A. Clemm, Ed. Internet Research Task Force (IRTF) A. Clemm, Ed.
Internet-Draft Independent Request for Comments: 9845 Independent
Intended status: Informational C. Pignataro, Ed. Category: Informational C. Pignataro, Ed.
Expires: 17 September 2025 NC State University ISSN: 2070-1721 NC State University
C. Westphal C. Westphal
L. Ciavaglia L. Ciavaglia
Nokia Nokia
J. Tantsura J. Tantsura
Nvidia Nvidia
M-P. Odini M-P. Odini
16 March 2025 August 2025
Challenges and Opportunities in Management for Green Networking Challenges and Opportunities in Management for Green Networking
draft-irtf-nmrg-green-ps-06
Abstract Abstract
Reducing humankind's environmental footprint and making technology Reducing humankind's environmental footprint and making technology
more environmentally sustainable are among the biggest challenges of more environmentally sustainable are among the biggest challenges of
our age. Networks play an important part in this challenge. On one our age. Networks play an important part in this challenge. On one
hand, they enable applications that help to reduce this footprint. hand, they enable applications that help to reduce this footprint.
On the other hand, they contribute to this footprint themselves in no On the other hand, they contribute to this footprint themselves in no
insignificant way. Therefore, methods to make networking technology insignificant way. Therefore, methods to make networking technology
itself "greener" and to manage and operate networks in ways that itself "greener" and to manage and operate networks in ways that
skipping to change at page 1, line 43 skipping to change at line 41
greenhouse gas emissions and less negative impact on the environment. greenhouse gas emissions and less negative impact on the environment.
This document is a product of the Network Management Research Group This document is a product of the Network Management Research Group
(NMRG) of the Internet Research Task Force (IRTF). This document (NMRG) of the Internet Research Task Force (IRTF). This document
reflects the consensus of the research group. It is not a candidate reflects the consensus of the research group. It is not a candidate
for any level of Internet Standard and is published for informational for any level of Internet Standard and is published for informational
purposes. purposes.
Status of This Memo Status of This Memo
This Internet-Draft is submitted in full conformance with the This document is not an Internet Standards Track specification; it is
provisions of BCP 78 and BCP 79. published for informational purposes.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at https://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months This document is a product of the Internet Research Task Force
and may be updated, replaced, or obsoleted by other documents at any (IRTF). The IRTF publishes the results of Internet-related research
time. It is inappropriate to use Internet-Drafts as reference and development activities. These results might not be suitable for
material or to cite them other than as "work in progress." deployment. This RFC represents the consensus of the Network
Management Research Group of the Internet Research Task Force (IRTF).
Documents approved for publication by the IRSG are not candidates for
any level of Internet Standard; see Section 2 of RFC 7841.
This Internet-Draft will expire on 17 September 2025. Information about the current status of this document, any errata,
and how to provide feedback on it may be obtained at
https://www.rfc-editor.org/info/rfc9845.
Copyright Notice Copyright Notice
Copyright (c) 2025 IETF Trust and the persons identified as the Copyright (c) 2025 IETF Trust and the persons identified as the
document authors. All rights reserved. document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents (https://trustee.ietf.org/ Provisions Relating to IETF Documents
license-info) in effect on the date of publication of this document. (https://trustee.ietf.org/license-info) in effect on the date of
Please review these documents carefully, as they describe your rights publication of this document. Please review these documents
and restrictions with respect to this document. carefully, as they describe your rights and restrictions with respect
to this document.
Table of Contents Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3 1. Introduction
1.1. Motivation . . . . . . . . . . . . . . . . . . . . . . . 3 1.1. Motivation
1.2. Approaching the Problem . . . . . . . . . . . . . . . . . 5 1.2. Approaching the Problem
1.3. Structuring the Problem Space . . . . . . . . . . . . . . 6 1.3. Structuring the Problem Space
2. Definitions and Acronyms . . . . . . . . . . . . . . . . . . 8 2. Definitions and Acronyms
3. Network Energy Consumption Characteristics and 3. Network Energy Consumption Characteristics and Implications
Implications . . . . . . . . . . . . . . . . . . . . . . 10 4. Challenges and Opportunities - Equipment Level
4. Challenges and Opportunities - Equipment Level . . . . . . . 12 4.1. Hardware and Manufacturing
4.1. Hardware and Manufacturing . . . . . . . . . . . . . . . 13 4.2. Visibility and Instrumentation
4.2. Visibility and Instrumentation . . . . . . . . . . . . . 14 5. Challenges and Opportunities - Protocol Level
5. Challenges and Opportunities - Protocol Level . . . . . . . . 15 5.1. Protocol Enablers for Carbon Optimization Mechanisms
5.1. Protocol Enablers for Carbon Optimization Mechanisms . . 16 5.2. Protocol Optimization
5.2. Protocol Optimization . . . . . . . . . . . . . . . . . . 17 5.3. Data Volume Reduction
5.3. Data Volume Reduction . . . . . . . . . . . . . . . . . . 18 5.4. Network Addressing
5.4. Network Addressing . . . . . . . . . . . . . . . . . . . 20 6. Challenges and Opportunities - Network Level
6. Challenges and Opportunities - Network Level . . . . . . . . 20
6.1. Network Optimization and Energy/Carbon/Pollution-Aware 6.1. Network Optimization and Energy/Carbon/Pollution-Aware
Networking . . . . . . . . . . . . . . . . . . . . . . . 21 Networking
6.2. Assessing Carbon Footprint and Network-Level 6.2. Assessing Carbon Footprint and Network-Level
Instrumentation . . . . . . . . . . . . . . . . . . . . . 22 Instrumentation
6.3. Dimensioning and Peak Shaving . . . . . . . . . . . . . . 23 6.3. Dimensioning and Peak Shaving
6.4. Convergence Schemes . . . . . . . . . . . . . . . . . . . 24 6.4. Convergence Schemes
6.5. The Role of Topology . . . . . . . . . . . . . . . . . . 25 6.5. The Role of Topology
7. Challenges and Opportunities - Architecture Level . . . . . . 25 7. Challenges and Opportunities - Architecture Level
8. Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . 27 8. Conclusions
9. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 28 9. IANA Considerations
10. Security Considerations . . . . . . . . . . . . . . . . . . . 28 10. Security Considerations
11. Contributors . . . . . . . . . . . . . . . . . . . . . . . . 29 11. Informative References
12. Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . 29 Acknowledgments
13. Informative References . . . . . . . . . . . . . . . . . . . 29 Contributors
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 33 Authors' Addresses
1. Introduction 1. Introduction
1.1. Motivation 1.1. Motivation
Climate change and the need to curb greenhouse gas (GHG) emissions Climate change and the need to curb greenhouse gas (GHG) emissions
have been recognized by the United Nations and by most governments as have been recognized by the United Nations and by most governments as
one of the big challenges of our time. As a result, curbing those one of the big challenges of our time. As a result, curbing those
emissions is becoming of increasing importance for society and for emissions is becoming increasingly important for society and for many
many industries. The networking industry is no exception. industries. The networking industry is no exception.
The science behind greenhouse gas emissions and their relationship The science behind greenhouse gas emissions and their relationship
with climate change is complex. However, there is overwhelming with climate change is complex. However, there is overwhelming
scientific consensus pointing towards a clear correlation between scientific consensus pointing toward a clear correlation between
climate change and a rising amount of greenhouse gases in the climate change and a rising amount of greenhouse gases in the
atmosphere. One greenhouse gas of particular concern, but by no atmosphere. One greenhouse gas of particular concern, but by no
means the only one, is carbon dioxide (CO2). Carbon dioxide is means the only one, is carbon dioxide (CO2). Carbon dioxide is
emitted in the process of burning fuels to generate energy that is emitted in the process of burning fuels to generate energy that is
used, for example, to power electrical devices such as networking used, for example, to power electrical devices such as networking
equipment. Notable here is the use of fossil fuels, such as oil, equipment. Notable here is the use of fossil fuels (such as oil,
which releases CO2 that had long been removed from the earth's which releases CO2 that has long been removed from the earth's
atmosphere, as opposed to the use of renewable or sustainable fuels atmosphere), as opposed to the use of renewable or sustainable fuels
that do not "add" to the amount of carbon in the atmosphere. There that do not "add" to the amount of CO2 in the atmosphere. There are
are additional gases associated with electricity generation, in additional gases associated with electricity generation, in
particular Methane (CH4) and Nitrous Oxide (N2O). Although in particular methane (CH4) and nitrous oxide (N2O). Although they
smaller quantities, they have an even higher Global Warming Potential exist in smaller quantities, they have an even higher Global Warming
(GWP). Potential (GWP).
Greenhouse gas emissions are in turn correlated with the need to Greenhouse gas emissions are in turn correlated with the need to
power technology, including networks. Reducing those emissions can power technology, including networks. Reducing those emissions can
be achieved by reducing the amount of fossil fuels needed to generate be achieved by reducing the amount of fossil fuels needed to generate
the energy that is needed to power those networks. This can be the energy that is needed to power those networks. This can be
achieved by improving the energy mix to include increasing amounts of achieved by improving the energy mix to include increasing amounts of
low-carbon and/or renewable (and hence sustainable) energy sources low-carbon and/or renewable (and hence sustainable) energy sources,
such as wind or solar. It can also be achieved by increasing energy such as wind or solar. It can also be achieved by increasing energy
savings and improving energy efficiency so that the same outcomes are savings and improving energy efficiency so that the same outcomes are
achieved while consuming less energy in the first place. achieved while consuming less energy in the first place.
The amount of greenhouse gases that an activity adds to the The amount of greenhouse gases that an activity adds to the
atmosphere, such as CO2 that is emitted in burning fossil fuels to atmosphere, such as CO2 that is emitted in burning fossil fuels to
generate the required energy, is also referred to as greenhouse generate the required energy, is also referred to as the "greenhouse
footprint, or carbon footprint (accounting for greenhouses gases footprint" or the "carbon footprint" (accounting for greenhouses
other than CO2 in terms of CO2 equivalents). Reducing this footprint gases other than CO2 in terms of CO2 equivalents). Reducing this
to net-zero is hence a major sustainability goal. However, footprint to net zero is hence a major sustainability goal. However,
sustainability encompasses also other factors beyond carbon, such as sustainability encompasses other factors beyond carbon, such as the
sustainable use of other natural resources, the preservation of sustainable use of other natural resources, the preservation of
natural habitats and biodiversity, and the avoidance of any form of natural habitats and biodiversity, and the avoidance of any form of
pollution. pollution.
In the context of this document, we refer to networking technology In the context of this document, we refer to networking technology
that helps to improve its own networking sustainability as "green". that helps to improve its own networking sustainability as "green".
Green, in that sense, includes technology that helps to lower Green, in that sense, includes technology that helps to lower
networking's greenhouse gas emissions including carbon footprint, networking's greenhouse gas emissions including the carbon footprint,
which turn includes technology that helps to increase efficiency and which in turn includes technology that helps increase efficiency and
realize energy savings as well as facilitating managing networks realize energy savings as well as facilitates managing networks
towards stronger use of renewables. toward a stronger use of renewables.
Arguably, networks can already be considered a "green" technology in Arguably, networks can already be considered a "green" technology in
that networks enable many applications that allow users and whole that networks enable many applications that allow users and whole
industries to save energy and thus become environmentally more industries to save energy and thus become environmentally more
sustainable in a significant way. For example, they allow (at least sustainable in a significant way. For example, they allow (at least
to an extent) to substitute travel with teleconferencing. They to an extent) to substitute travel with teleconferencing. They
enable many employees to work from home and "telecommute", thus enable many employees to work from home and telecommute, thus
reducing the need for actual commute. IoT applications that reducing the need for actual commuting. IoT applications that
facilitate automated monitoring and control from remote sites help facilitate automated monitoring and control from remote sites help
make agriculture more sustainable by minimizing the application of make agriculture more sustainable by minimizing the usage of water,
resources such as water and fertilizer as well as land use. fertilizer, and land area. Networked smart buildings allow for
Networked smart buildings allow for greater energy optimization and greater energy optimization and sparser use of lighting and HVAC
sparser use of lighting and HVAC (heating, ventilation, air (heating, ventilation, air conditioning) than their non-networked,
conditioning) than their non-networked not-so-smart counterparts. not-so-smart counterparts. That said, calculating precise benefits
That said, calculating precise benefits in terms of net in terms of net sustainability contributions and savings is complex,
sustainability contributions and savings is complex as a holistic as a holistic picture involves many effects including substitution
picture involves many effects, including substituion effects (perhaps effects (perhaps saving on emissions caused by travel but incurring
saving on emissions caused by travel but incurring additional cost additional costs associated with additional home office use) as well
associated with additional home office use) as well as behavioral as behavioral changes (perhaps a higher number of meetings than if
changes (perhaps higher number of meetings than if travel were travel were involved).
involved).
The IETF has recently initiated a reflection on the energy cost of The IETF has recently initiated a reflection on the energy cost of
hosting meetings three times a year (see for instance [IETF-Net0]). hosting meetings three times a year (see [IETF-Net0]). It conducted
It conducted a study of the carbon emissions of a typical meeting and a study of the carbon emissions of a typical meeting and found out
found out that 99% of the emissions were due to the air travel. In that 99% of the emissions were due to air travel. In the same vein,
the same vein, [Framework] compared an in-person with a virtual [Framework] compared an in-person with a virtual meeting and found a
meeting and found a reduction in energy of 66% for a virtual meeting. reduction in energy of 66% for a virtual meeting. These findings
These findings confirm that networking technology can reduce confirm that networking technology can reduce emissions when acting
emissions when acting as virtual substitution for physical events. as a virtual substitution for physical events.
That said, networks themselves consume significant amounts of energy. That said, networks themselves consume significant amounts of energy.
Therefore, the networking industry has an important role to play in Therefore, the networking industry has an important role to play in
meeting sustainability goals not just by enabling others to reduce meeting sustainability goals and not just by enabling others to
their reliance on energy, but by also reducing its own. Future reduce their reliance on energy but by also reducing its own. Future
networking advances will increasingly need to focus on becoming more networking advances will increasingly need to focus on becoming more
energy-efficient and reducing carbon footprint, both for economic energy efficient and reducing the carbon footprint, for reasons of
reasons and for reasons of corporate responsibility. This shift has both corporate responsibility and economics. This shift has already
already begun, and sustainability is already becoming an important begun, and sustainability is becoming an important concern for
concern for network providers. In some cases, such as in the context network providers. In some cases, such as in the context of
of networked data centers, the ability to procure enough energy networked data centers, the ability to procure enough energy becomes
becomes a bottleneck prohibiting further growth and greater a bottleneck, prohibiting further growth, and greater sustainability
sustainability thus becomes a business necessity. thus becomes a business necessity.
For example, in its annual report, Telefónica reports that in 2021, For example, in its annual report, Telefónica reports that in 2021,
its network's energy consumption per PB of data amounted to 54MWh its network's energy consumption per petabyte (PB) of data amounted
[Telefonica2021]. This rate has been dramatically decreasing (a to 54 megawatt-hours (MWh) [Telefonica2021]. This rate has been
seven-fold factor over six years) although gains in efficiency are dramatically decreasing (by a factor of seven over six years),
being offset by simultaneous growth in data volume. In the same although gains in efficiency are being offset by simultaneous growth
report, it is stated as an important corporate goal to continue on in data volume. The same report states that an important corporate
that trajectory and aggressively reduce overall carbon emissions goal is continuing on that trajectory and aggressively reducing
further. overall carbon emissions further.
1.2. Approaching the Problem 1.2. Approaching the Problem
An often-considered gain in networking sustainability can be made An often-considered gain in networking sustainability can be made
with regards to improving the efficiency with which networks utilize with regards to improving the efficiency with which networks utilize
power during their use phase, reducing the amount of energy that is power during their use phase, reducing the amount of energy that is
required to provide communication services. However, for a holistic required to provide communication services. However, for a holistic
approach other aspects need to be considered as well. approach, other aspects need to be considered as well.
Environmental footprint is determined not by energy consumption The environmental footprint is not determined by energy consumption
alone. The sustainability of power sources needs to be considered as alone. The sustainability of power sources needs to be considered as
well. A deployment that includes devices that are less energy- well. A deployment that includes devices that are less energy
efficient but that are powered by a sustainable energy source can efficient but powered by a sustainable energy source can arguably be
arguably be considered "greener" than a deployment that includes considered "greener" than a deployment that includes highly efficient
highly efficient device that are powered by Diesel generators. In devices that are powered by diesel generators. In fact, in the same
fact, in the same Telefónica report mentioned earlier, extensive Telefónica report mentioned earlier, extensive reliance on renewable
reliance on renewable energy sources is emphasized. energy sources is emphasized.
Similarly, deployments can take other environmental factors into Similarly, deployments can take other environmental factors into
account that affect carbon footprint. For example, deployments in account that affect the carbon footprint. For example, deployments
which factors such as the need for cooling are reduced, or where where the need for cooling is reduced or where excessive heat
excessive heat that is generated by equipment can be put to generated by equipment can be put to a productive use will be
productive use, will be considered greener than deployments where considered greener than deployments where this is not the case.
this is not the case. Examples include deployments in cooler natural Examples include deployments in cooler natural surroundings (e.g., in
surroundings (e.g., in colder climates) where that is an option. colder climates) where that is an option. Likewise, manufacturing
Likewise, manufacturing and recycling of networking equipment are and recycling networking equipment are also part of the
also part of the sustainability equation, as the production itself sustainability equation, as the production itself consumes energy and
consumes energy and results in a carbon cost embedded as part of the results in a carbon cost embedded as part of the device itself.
device itself. Extending the lifetime of equipment may in many cases Extending the lifetime of equipment may in many cases be preferable
be preferable over replacing it earlier with equipment that is over replacing it earlier with equipment that is slightly more energy
slightly more energy-efficient but that requires the embedded carbon efficient, but that requires the embedded carbon cost to be amortized
cost to be amortized over a much shorter period of time. over a much shorter period of time.
Management has an outsized role to play in approaching those Management has an outsized role to play in approaching those
problems. To reduce the amount of energy used, network providers problems. To reduce the amount of energy used, network providers
need to maximize ways in which they make use of scarce resources and need to maximize ways in which they use scarce resources and
eliminate use of resources which are not needed. They need to eliminate the use of unneeded resources. They need to optimize the
optimize the way in which networks are deployed, which resources are way in which networks are deployed, which resources are placed where,
placed where, how equipment lifecycles and upgrades are being managed and how equipment lifecycles and upgrades are being managed -- all of
- all of which constitute classic operational problems. As best which constitute classic operational problems. As best practices,
practices, methods, and algorithms are developed, they need to be methods, and algorithms are developed, they need to be automated to
automated to the greatest extent possible and migrated over time into the greatest extent possible, migrated over time into the network,
the network and performed on increasingly short time scales, and performed on increasingly short timescales, transcending
transcending management and control planes. management and control planes.
1.3. Structuring the Problem Space 1.3. Structuring the Problem Space
From a technical perspective, multiple vectors along which networks From a technical perspective, multiple vectors along which networks
can be made "greener" should be considered: can be made "greener" should be considered:
* Equipment level: * Equipment level:
Perhaps the most promising vector for improving networking Perhaps the most promising vector for improving networking
sustainability concerns the network equipment itself. At the most sustainability concerns the network equipment itself. At the most
fundamental level, networks (even softwarized ones) involve fundamental level, networks (even softwarized ones) involve
appliances, i.e., equipment that relies on electrical power to appliances, i.e., equipment that relies on electrical power to
perform its function. There are two distinct layers with perform its function. There are two distinct layers with
different opportunities for improvement: different opportunities for improvement:
- Hardware: Reducing embedded carbon during material extraction - Hardware: Reducing embedded carbon during material extraction
and manufacturing, improving energy efficiency and reducing and manufacturing, improving energy efficiency, and reducing
energy consumption during operations, and reuse, repurpose, and energy consumption during operations, and reuse, repurpose, and
recycle motions. recycle motions.
- Software: Improving software energy efficiency, maximizing - Software: Improving software energy efficiency, maximizing
utilization of processing devices, allowing for software to utilization of processing devices, and allowing for software to
interact with hardware to improve sustainability. interact with hardware to improve sustainability.
Beyond making network appliances merely more energy-efficient, Beyond making network appliances merely more energy efficient,
there are other important ways in which equipment can help there are other important ways in which equipment can help
networks become greener. This includes aspects such as support networks become greener. This includes aspects such as supporting
for port power saving modes or down-speeding of links to reduce port power-saving modes or down-speeding links to reduce power
power consumption for resources that are not fully utilized. To consumption for resources that are not fully utilized. To fully
fully tap into the potential of such features requires tap into the potential of such features, it requires accompanying
accompanying management functionality, for example to determine management functionality, for example, to determine when it is
when it is "safe" to down-speed a link or enter a power saving "safe" to down-speed a link or to enter a power-saving mode, and
mode, and manage the network in such a way that conditions to do to maximize the conditions when that action is appropriate.
so are maximized.
Most importantly from a management perspective, improving Most importantly, from a management perspective, improving
sustainability at the equipment level involves providing sustainability at the equipment level involves providing
management instrumentation that allows to precisely monitor and management instrumentation that allows for precise monitoring and
manage power usage and doing so at different levels of managing power usage and doing so at different levels of
granularity, for example accounting separately for the granularity, for example, accounting separately for the
contributions of CPU, memory, and different ports. This enables contributions of CPU, memory, and different ports. This enables
(for example) controller applications to optimize energy usage (for example) controller applications to optimize energy usage
across the network and that leverage control loops to assess the across the network and to leverage control loops to assess the
effectiveness (e.g. in terms of reduction in power use) of effectiveness (e.g., in terms of reducing power use) of the
measures that are taken. measures that are taken.
As a side note, the terms "device" and "equipment", as used in the As a side note, the terms "device" and "equipment", as used in the
context of this draft, are used to refer to networking equipment. context of this document, are used to refer to networking
We are not taking into consideration end-user devices and equipment. We are not taking into consideration end-user devices
endpoints such as mobile phones or computing equipment. and endpoints such as mobile phones or computing equipment.
* Protocol level: * Protocol level:
Energy-efficiency and greenness are aspects that are rarely Energy-efficiency and greenness are aspects that are rarely
considered when designing network protocols. This suggests that considered when designing network protocols. This suggests that
there may be plenty of untapped potential. Some aspects involve there may be plenty of untapped potential. Some aspects involve
designing protocols in ways that reduce the need for redundant or designing protocols in ways that reduce the need for redundant or
wasteful transmission of data to allow not only for better network wasteful transmission of data, allowing not only for better
utilization, but greater goodput per unit of energy being network utilization but for greater goodput per unit of energy
consumed. Techniques might include approaches that reduce the being consumed. Techniques might include approaches that reduce
"header tax" incurred by payloads as well as methods resulting in the "header tax" incurred by payloads as well as methods resulting
the reduction of wasteful retransmissions. Similarly, there may in the reduction of wasteful retransmissions. Similarly, there
be cases where chattiness of protocols may be preventing equipment may be cases where chattiness of protocols may be preventing
from going into sleep mode. Designing protocols that reduce equipment from going into sleep mode. Designing protocols that
chattiness in such scenarios, for example, that reduce dependence reduce chattiness in such scenarios, for example, that reduce
on periodic updates or heartbeats, may result in greener outcomes. dependence on periodic updates or heartbeats, may result in
Likewise, aspects such as restructuring addresses in ways that greener outcomes. Likewise, aspects such as restructuring
allow to minimize the size of lookup tables and associated memory addresses in ways that minimize the size of lookup tables,
sizes and hence energy use can play a role as well. associated memory sizes, and hence energy use, can play a role as
well.
Another role of protocols concerns the enabling of management Another role of protocols concerns the enabling of management
functionality to improve energy efficiency at the network level, functionality to improve energy efficiency at the network level,
such as discovery protocols that allow for quick adaptation to such as discovery protocols that allow for quick adaptation to
network components being taken dynamically into and out of service network components being taken dynamically into and out of service
depending on network conditions, as well as protocols that can depending on network conditions, as well as protocols that can
assist with functions such as the collection of energy telemetry assist with functions such as the collection of energy telemetry
data from the network. data from the network.
* Network level * Network level:
Perhaps the greatest opportunities to realize power savings exist Perhaps the greatest opportunities to realize power savings exist
at the level of the network as whole. Many of these opportunities at the level of the network as whole. Many of these opportunities
are directly related to management functionality. For example, are directly related to management functionality. For example,
optimizing energy efficiency may involve directing traffic in such optimizing energy efficiency may involve directing traffic in such
a way that it allows for isolation of equipment that might not be a way that it allows the isolation of equipment that might not be
needed at certain moments so that it can be powered down or needed at certain moments so that it can be powered down or
brought into power-saving mode. By the same token, traffic should brought into power-saving mode. By the same token, traffic should
be directed in a way that requires bringing additional equipment be directed in a way that requires bringing additional equipment
online or out of power-saving mode in cases where alternative online or out of power-saving mode in cases where alternative
traffic paths are available for which the incremental energy cost traffic paths are available for which the incremental energy cost
would amount to zero. Likewise, some networking devices may be would amount to zero. Likewise, some networking devices may be
rated less "green" and more power-intensive than others or powered rated less "green" and more power-intensive than others or may be
by less-sustainable energy sources. Their use might be avoided powered by less-sustainable energy sources. Their use might be
unless during periods of peak capacity demands. Generally, avoided except during periods of peak capacity demands.
incremental carbon emissions can be viewed as a cost metric that Generally, incremental carbon emissions can be viewed as a cost
networks should strive to minimize and consider as part of routing metric that networks should strive to minimize and consider as
and of network path optimization. part of routing and network path optimization.
* Architecture level * Architecture level:
The current network architecture supports a wide range of The current network architecture supports a wide range of
applications, but does not consider energy efficiency as one of applications but does not consider energy efficiency as one of its
its design parameters. One can argue that the most energy design parameters. One can argue that the most energy efficient
efficient shift of the last two decades has been the deployment of shift of the last two decades has been the deployment of Content
Content Delivery Network overlays: while these were set up to Delivery Network overlays: while these were set up to reduce
reduce latency and minimize bandwidth consumption, from a network latency and minimize bandwidth consumption, from a network
perspective, retrieving the content from a local cache is also perspective, retrieving the content from a local cache is also
much greener. What other architectural shifts can produce energy much greener. What other architectural shifts can produce energy
consumption reduction? consumption reduction?
In this document, we will explore each of those vectors in further In this document, we will explore each of those vectors in further
detail and attempt to articulate specific challenges that could make detail and attempt to articulate specific challenges that could make
a difference when addressed. As our starting point, we borrow some a difference when addressed. As our starting point, we borrow some
material from a prior paper, [GreenNet22]. For this document, this material from "Challenges and Opportunities in Green Networking"
material has been both expanded (for example, in terms of some of the [GreenNet22]. For this document, this material has been both
opportunities) and pruned (for example, in terms of background on expanded (for example, in terms of some of the opportunities) and
prior scholarly work). pruned (for example, in terms of background on prior scholarly work).
This document is a product of the Network Management Research Group This document is a product of the Network Management Research Group
(NMRG) of the Internet Research Task Force (IRTF). This document (NMRG) of the Internet Research Task Force (IRTF). This document
reflects the consensus of the research group and was discussed and reflects the consensus of the research group and was discussed and
presented multiple times, each time receiving positive feedback and presented multiple times, each time receiving positive feedback and
no objections. It is not a candidate for any level of Internet no objections. It is not a candidate for any level of Internet
Standard and is published for informational purposes. Standard and is published for informational purposes.
2. Definitions and Acronyms 2. Definitions and Acronyms
Below you find acronyms used in this draft: Below you find acronyms used in this document:
Carbon Footprint: Carbon Footprint: As used in this document, the amount of carbon
As used in this document, the amount of carbon emissions emissions associated with the use or deployment of technology,
associated with the use or deployment of technology, usually usually correlated with the amount of energy consumption
correlated with the amount of energy consumption
CDN: Content Delivery Network CDN: Content Delivery Network
CPU: Central Processing Unit, that is the main processor in a CPU: Central Processing Unit (that is, the main processor in a
server server)
DC: Data Center DC: Data Center
FCT: Flow Completion Time FCT: Flow Completion Time
GHG: Greenhouse Gas GHG: Greenhouse Gas
GPU: Graphical Processing Unit GPU: Graphical Processing Unit
HVAC: Heating, Ventilation, Air Conditioning HVAC: Heating, Ventilation, Air Conditioning
ICN: Information Centric Network ICN: Information-Centric Network
IGP: Interior Gateway Protocol IGP: Interior Gateway Protocol
IoT: Internet of Things IoT: Internet of Things
IPU: Infrastructure Processing Units IPU: Infrastructure Processing Unit
LEED: Leadership in Energy and Environmental Design, a green LEED: Leadership in Energy and Environmental Design (a green
building rating system building rating system)
LEO: Low Earth Orbit LEO: Low Earth Orbit
LPM: Longest Prefix Match, a method to look up prefixes in a LPM: Longest Prefix Match (a method to look up prefixes in a
forwarding element forwarding element)
MPLS: Multi-Path Label Switchin MPLS: Multiprotocol Label Switching
MTU: Maximum Transmission Unit, the largest packet size that can be MTU: Maximum Transmission Unit (the largest packet size that can be
transmitted over a network transmitted over a network)
NIC: Network Interface Card NIC: Network Interface Card
QoE: Quality of Experience QoE: Quality of Experience
QoS: Quality of Service QoS: Quality of Service
QUIC: Quick UDP Internet Connections QUIC: Quick UDP Internet Connections
SNIC: Smart NIC SDN: Software-Defined Networking
SDN: Software-Defined Networking TCP: Transport Control Protocol
TCP: Transport Control Protocol
TE: Traffic Engineering TE: Traffic Engineering
TPU: Tensor Processing Unit TPU: Tensor Processing Unit
WAN: Wide Area Network WAN: Wide Area Network
3. Network Energy Consumption Characteristics and Implications 3. Network Energy Consumption Characteristics and Implications
Carbon footprint and, with it, greenhouse gas emissions are The carbon footprint and, with it, greenhouse gas emissions are
determined by several factors. A main factor is network energy determined by several factors. A main factor is network energy
consumption, as the energy consumed can be considered a proxy for the consumption, as the energy consumed can be considered a proxy for the
burning of fuels required for corresponding power generation. burning of fuels required for corresponding power generation.
Network energy consumption by itself does not tell the whole story, Network energy consumption by itself does not tell the whole story,
as it does not take the sustainability of energy sources and energy as it does not take the sustainability of energy sources and the
mix into account. Likewise, there are other factors such as hidden energy mix into account. Likewise, there are other factors such as
carbon cost reflecting the carbon footprint expended in manufacturing the carbon cost expended in the manufacturing of networking hardware.
of networking hardware. Nonetheless, network energy consumption is Nonetheless, network energy consumption is an excellent predictor of
an excellent predictor for carbon footprint and its reduction key to a carbon footprint and its reduction, which is key to sustainable
sustainable solutions. Exploring possibilities to improve energy solutions. Hence, exploring possibilities to improve energy
efficiency is hence a key factor for greener, more sustainable, less efficiency is a key factor for greener, more sustainable, less
carbon-intensive networks. carbon-intensive networks.
For this, it is important to understand some of the characteristics It is important to understand some of the characteristics of power
of power consumption by networks and which aspects contribute the consumption by networks and which aspects contribute the most. This
most. This helps to identify where the greatest potential not just helps to identify where the greatest potential is, not just for power
for power savings but also for sustainability improvements lies. savings but also for sustainability improvements.
Power is ultimately drawn by devices. Devices are not monoliths but Power is ultimately drawn by devices. Devices are not monoliths but
are composed of multiple components. The power consumption of the are composed of multiple components. The power consumption of the
device can be divided into the consumption of the core device - the device can be divided into the consumption of the core device -- the
backplane and CPU, if you will - as well as additional consumption backplane and CPU, if you will -- as well as additional consumption
incurred per port and line card. In addition, GPU and TPU may be incurred per port and line card. In addition, the GPU and TPU may be
used as well in the network and may have different power consumption used in the network and may have different power consumption
profiles. Furthermore, it is important to understand the difference profiles. Furthermore, it is important to understand the difference
between power consumption when a resource is idling versus when it is between power consumption when a resource is idling versus when it is
under load. This helps to understand the incremental cost of under load. This helps to understand the incremental cost of
additional transmission versus the initial cost of transmission. additional transmission versus the initial cost of transmission.
In typical networking devices, only roughly half of the energy In typical networking devices, only roughly half of the energy
consumption is associated with the data plane [Bolla2011energy]. An consumption is associated with the data plane [Bolla2011energy]. An
idle base system typically consumes more than half of the energy over idle base system typically consumes more than half of the energy that
the same system running at full load [Chabarek08], [Cervero19]. the same system would consume when running at full load [Chabarek08]
Generally, the cost of sending the first bit is very high, as it [Cervero15]. Generally, the cost of sending the first bit is very
requires powering up a device, port, etc. The incremental energy high, as it requires powering up a device, port, etc. The
cost of transmission of additional bits (beyond the first) is many incremental energy cost of transmission of additional bits (beyond
orders of magnitude lower. Likewise, the incremental cost of the first) is many orders of magnitude lower. Likewise, the
incremental CPU and memory needed to process additional packets incremental cost of the incremental CPU and memory needed to process
becomes fairly negligible. additional packets becomes fairly negligible.
This means that a device's energy consumption does not increase This means that a device's energy consumption does not increase
linearly with the volume of forwarded traffic. Instead, it resembles linearly with the volume of forwarded traffic. Instead, it resembles
more of a step function in which energy consumption stays roughly the a step function in which energy consumption stays roughly the same up
same up to a certain volume of traffic, followed by a sudden jump to a certain volume of traffic, followed by a sudden jump when
when additional resources need to be procured to support a higher additional resources need to be procured to support a higher volume
volume of traffic. of traffic.
By the same token, it is generally more energy-efficient to transmit By the same token, it is generally more energy efficient to transmit
a large volume of data in one burst (and subsequently turning off or a large volume of data in one burst (and subsequently turn off or
down-speeding the interface when idling) than to continuously down-speed the interface when idling) than to continuously transmit
transmit at a lower rate. In that sense it can be the duration of at a lower rate. In that sense, it can be the duration of the
the transmission that dominates the energy consumption, not the transmission that dominates the energy consumption -- not the actual
actual data rate. data rate.
The implications on green networking from an energy-savings The implications on green networking from an energy-savings
standpoint are significant. Of utmost importance are schemes that standpoint are significant. Of utmost importance are schemes that
allow for "peak shaving": networks are typically dimensioned for allow for "peak shaving": networks are typically dimensioned for
periods of peak demand and usage, yet any excess capacity during periods of peak demand and usage, yet any excess capacity during
periods of non-peak usage does not result in corresponding energy periods of non-peak usage does not result in corresponding energy
savings. Peak shaving techniques that allow to reduce peak traffic savings. Peak shaving techniques that reduce peak traffic spikes and
spikes and thus waste during non-peak periods may result in outsize waste during non-peak periods may result in outsize sustainability
sustainability gains. Peak shaving could be accomplished by gains. Peak shaving could be accomplished by techniques such as
techniques such as spreading spikes out over geographies (e.g. spreading spikes out over geographies (e.g., routing traffic across
routing traffic across more costly but less utilized routes) or over more costly but less utilized routes) or over time (e.g., postponing
time (e.g. postponing and buffering non-urgent traffic). and buffering non-urgent traffic).
Likewise, large gains can be made whenever network resources can Likewise, large gains can be made whenever network resources can
effectively be taken offline for at least some of the time, managing effectively be taken offline for at least some of the time, managing
networks in a way that enables resources to be removed from service networks in a way that enables resources to be removed from service
so they can be powered down (or put into a more energy-saving state, so they can be powered down (or put into a more energy-saving state,
such as when down-speeding ports) while not needed. Of course, any such as when down-speeding ports) while not needed. Of course, any
such methods need to take into account the overhead of taking such methods need to take into account the overhead of taking
resources offline and bringing them back online. This typically resources offline and bringing them back online. This typically
takes some amount of time, requiring accurate predictive capabilities takes some amount of time, requiring accurate predictive capabilities
to avoid situations in which network resources are not available at to avoid situations in which network resources are not available at
times when they would be needed. In addition, there is additional times when they would be needed. In addition, there is additional
overhead such as synchronization of state to be accounted for. overhead, such as synchronization of state, to be accounted for.
At the same time, any non-idle resources should be utilized to the At the same time, any non-idle resources should be utilized to the
greatest extent possible as the incremental energy cost is greatest extent possible, as the incremental energy cost is
negligible. Of course, this needs to occur while still taking other negligible. Of course, this needs to occur while still taking other
operational goals into consideration, such as protection against operational goals into consideration, such as protection against
failures (allowing for readily available redundancy and spare failures (allowing for readily available redundancy and spare
capacity in case of failure) and load balancing (for increased capacity in case of failure) and load balancing (for increased
operational robustness). As data transmission needs tend to operational robustness). As data transmission needs tend to
fluctuate wildly and occur in bursts, any optimization schemes need fluctuate wildly and occur in bursts, any optimization schemes need
to be highly adaptable and allow for control loops at very fast time to be highly adaptable and allow control loops at very fast time
scales. scales.
Similarly, for applications where this is possible, it may be Similarly, for applications where this is possible, it may be
desirable to replace continuous traffic at low data rates with desirable to replace continuous traffic at low data rates with
traffic that is sent in burst at high data rates in order to traffic that is sent in bursts at high data rates in order to
potentially maximize the time during which resources can be idled. potentially maximize the time during which resources can be idled.
As a result, emphasis needs to be given to technology that allows for As a result, emphasis needs to be given to technology that allows,
example to (at the device level) exercise very efficient and rapid for example, (at the device level) very efficient and rapid
discovery, monitoring, and control of networking resources so that discovery, monitoring, and control of networking resources so that
they can be dynamically be taken offline or back into service, they can be dynamically taken offline or brought back in service
without (at the network level) requiring extensive convergence of without (at the network level) requiring an extensive convergence of
state across the network or recalculation of routes and other state across the network or a recalculation of routes and other
optimization problems, and (at the network equipment level) support optimization problems, and (at the network equipment level) support
rapid power cycle and initialization schemes. There may be some rapid power cycle and initialization schemes. There may be some
lessons that can be applied here from IoT, which has long had to lessons that can be applied here from IoT, which has long had to
contend with power-constrained end devices that need to spend much of contend with power-constrained end devices that need to spend much of
their time in power saving states to conserve battery. their time in power-saving states to conserve battery.
4. Challenges and Opportunities - Equipment Level 4. Challenges and Opportunities - Equipment Level
We are categorizing challenges and opportunities to improve We are categorizing challenges and opportunities to improve
sustainability at the network equipment level along the following sustainability at the network equipment level along the following
lines: lines:
* Hardware and manufacturing. Related opportunities are arguably * Hardware and manufacturing: Related opportunities are arguably
among the most obvious and perhaps "largest". However, solutions among the most obvious and perhaps "largest". However, solutions
here lie largely outside the scope of networking researchers. here lie largely outside the scope of networking researchers.
* Visibility and instrumentation. Instrumenting equipment to * Visibility and instrumentation: Instrumenting equipment to provide
provide visibility into how they consume energy is key to visibility into how they consume energy is key to management
management solutions and control loops to facilitate optimization solutions and control loops to facilitate optimization schemes.
schemes.
4.1. Hardware and Manufacturing 4.1. Hardware and Manufacturing
Perhaps the most obvious opportunities to make networking technology Perhaps the most obvious opportunities to make networking technology
more energy efficient exist at the equipment level. After all, more energy efficient exist at the equipment level. After all,
networking involves physical equipment to receive and transmit data. networking involves physical equipment to receive and transmit data.
Making such equipment more power efficient, have it dissipate less Making such equipment more power efficient, having it dissipate less
heat to consume less energy and reduce the need for cooling, making heat to consume less energy and reduce the need for cooling, making
it eco-friendly to deploy, sourcing sustainable materials and it eco-friendly to deploy, sourcing sustainable materials, and
facilitating recycling of equipment at the end of its lifecycle all facilitating the recycling of equipment at the end of its lifecycle
contribute to making networks greener. More specific and unique to -- all contribute to making networks greener. Reducing the energy
networking are schemes to reduce energy usage of transmission usage of transmission technology, from wireless (antennas) to optical
technology from wireless (antennas) to optical (lasers). (lasers), is a strategy that is unique to networking.
One critical aspect of the energy cost of networking is the cost to One critical aspect of the energy cost of networking is the cost to
manufacture and deploy the networking equipment. In addition, even manufacture and deploy the networking equipment. In addition, even
the development process itself comes with its own carbon footprint. the development process itself comes with its own carbon footprint.
This is outside of the scope of this document: we only consider the This is outside of the scope of this document: we only consider the
energy cost of running the network that applies during the energy cost of running the network during the operational part of the
operational part of the equipment's lifecycle. However, a holistic equipment's lifecycle. However, a holistic approach would include
approach would include into this the embedded energy that is included the embedded energy that is included in the networking equipment. As
in the networking equipment. As part of this, aspects such as the part of this, aspects such as the impact of deploying new protocols
impact of deploying new protocols on the rate of obsolescence of on the rate of obsolescence of existing equipment should be
existing equipment should be considered. For instance, incremental considered. For instance, incremental approaches that do not require
approaches that do not require to replace equipment right away - or replacing equipment right away -- or even that extend the lifetime of
even extend the lifetime of deployed equipment - would have a lower deployed equipment -- would have a lower energy footprint. This is
energy footprint. This is one important benefit also of technologies one important benefit also of technologies such as Software-Defined
such as Software-Defined Networking and Network Function Networking and network function virtualization, as they may allow
Virtualization, as they may allow support of new networking features support for new networking features through software updates without
through software updates without requiring hardware replacements. requiring hardware replacements.
An attempt to compute not only the energy of running a network, but [Emergy] describes an attempt to compute not only the energy of
also the energy embedded into manufacturing the equipment is running a network but also the energy embedded into manufacturing the
described in [Emergy] . This is denoted by "emergy", a portmanteau equipment. This is denoted by "emergy", a portmanteau for embedded
for embedded energy. Likewise, an approach to recycling equipment energy. Likewise, [Junkyard] describes an approach to recycling
and a proof of concept using old cell phones recycled into a equipment and a proof of concept using old mobile phones recycled
"junkyard" data center are described in [Junkyard]. into a "junkyard" data center.
One trade-off to consider at this level is the selection of a One trade-off to consider at this level is the selection of a
platform that can be hardware-optimized for energy efficiency vs a platform that can be hardware-optimized for energy efficiency versus
platform that is versatile and can run multiple functions. For a platform that is versatile and can run multiple functions. For
instance, a switch could run on an efficient hardware platform, or instance, a switch could run on an efficient hardware platform or run
run as a software module (container) over some multi-purpose as a software module (container) over some multipurpose platform.
platform. While the first one is operationally more energy While the first one is operationally more energy efficient, it may
efficient, it may have a higher embedded energy from a smaller scale, have a higher embedded energy from a smaller scale, a less efficient
less efficient production process, as well as a shorter shelf life production process, as well as a shorter shelf life once new
once new functions need to be added to the platform. functions need to be added to the platform.
4.2. Visibility and Instrumentation 4.2. Visibility and Instrumentation
Beyond "first-order" opportunities as outlined in the previous Beyond "first-order" opportunities, as outlined in Section 4.1,
subsection, network equipment just as importantly plays an important network equipment just as importantly plays a role in enabling and
role to enable and support green networking at other levels. Of supporting green networking at other levels. Of prime importance is
prime importance is the equipment's ability to provide visibility to the equipment's ability to provide visibility to the management and
management and control plane into its current energy usage. Such control planes into its current energy usage. Such visibility
visibility enables control loops for energy optimization schemes, enables control loops for energy optimization schemes, allowing
allowing applications to obtain feedback regarding the energy applications to obtain feedback regarding the energy implications of
implications of their actions, from setting up paths across the their actions, from setting up paths across the network that require
network that require the least incremental amount of energy to the least incremental amount of energy to quantifying metrics related
quantifying metrics related to energy cost used to optimize to energy cost to optimize forwarding decisions. Absent an actual
forwarding decisions. Absent an actual measurement of energy usage measurement of energy usage (and until such measurement is put in
(and until such measurement is put in place), the network equipment place), the network equipment could advertise some proxy of its power
could advertise some proxy of its power consumption (say, a labelling consumption. For example, it could use a labeling scheme of silver,
scheme as silver, gold, platinum similar to the LEED sustainability gold, or platinum similar to the LEED sustainability metric in
metric in building codes or the Energy Star label in home appliances; building codes, or the Energy Star label in home appliances, or a
or a description of the type of the device as using CPU vs GPU vs TPU description of the type of the device as using CPU vs. GPU vs. TPU
processors with different power profiles). processors with different power profiles.
One prerequisite to such schemes is to have proper instrumentation in One prerequisite to such schemes is to have proper instrumentation in
place that allows to monitor current power consumption at the level place that allows for monitoring current power consumption at the
of networking devices as a whole, line cards, and individual ports. level of networking devices as a whole, line cards, and individual
Such instrumentation should also allow to assess the energy ports. Such instrumentation should also allow for assessing the
efficiency and carbon footprint of the device as a whole. In energy efficiency and carbon footprint of the device as a whole. In
addition, it will be desirable to relate this power consumption to addition, it will be desirable to relate this power consumption to
data rates as well as to current traffic, for example, to indicate data rates and to current traffic, for example, to indicate current
current energy consumption relative to interface speeds, as well as energy consumption relative to interface speeds, as well as for
for incremental energy consumption that is expected for incremental incremental energy consumption that is expected for incremental
traffic (to aid control schemes that aim to "shave" power off current traffic (to aid control schemes that aim to "shave" power off current
services or to minimize the incremental use of power for additional services or to minimize the incremental use of power for additional
traffic). This is an area where the current state of the art is traffic). This is an area where the current state of the art is
sorely lacking and standardization lags behind. For example, as of sorely lacking, and standardization lags behind. For example, as of
today, standardized YANG data models [RFC7950] for network energy today, standardized YANG data models [RFC7950] for network energy
consumption that can be used in conjunction with management and consumption that can be used in conjunction with management and
control protocols have yet to be defined. control protocols have yet to be defined.
To remedy this situation, efforts to define sets of green networking To remedy this situation, efforts to define sets of green networking
metrics [I.D.draft-cx-green-green-metrics] as well as YANG data metrics [GREEN_METRICS] as well as YANG data models that include
models that include objects that provide visibility into power objects that provide visibility into power measurements (e.g.,
measurements (e.g. [I.D.draft-li-green-power]) are getting underway. [POWER_YANG]) were underway in 2024. Agreed sets of metrics and
Agreed sets of metrics and corresponding data models will provide the corresponding data models will provide the basis for further steps,
basis for further steps, beginning with their implementation as part beginning with their implementation as part of management and control
of management and control instrumentation. instrumentation.
Instrumentation should also take into account the possibility of Instrumentation should also take into account the possibility of
virtualization, introducing layers of indirection to assess the virtualization, introducing layers of indirection to assess the
actual energy usage. For example, virtualized networking functions actual energy usage. For example, virtualized networking functions
could be hosted on containers or virtual machines which are hosted on could be hosted on containers or virtual machines that are hosted on
a CPU in a data center instead of a regular network appliance such as a CPU in a data center instead of a regular network appliance such as
a router or a switch, leading to very different power consumption a router or a switch, leading to very different power consumption
characteristics. For example, a data center CPU could be more power characteristics. For example, a data center CPU's power consumption
efficient and consume power more proportionally to actual CPU load. could be more efficient and more proportional to actual CPU load.
Instrumentation needs to reflect these facts and facilitate Instrumentation needs to reflect these facts and facilitate
attributing power consumption in a correct manner. attributing power consumption in a correct manner.
Beyond monitoring and providing visibility into power consumption, Beyond monitoring and providing visibility into power consumption,
control knobs are needed to configure energy saving policies. For control knobs are needed to configure energy-saving policies. For
instance, power saving modes are common in endpoints (such as mobile instance, power-saving modes are common in endpoints (such as mobile
phones or notebook computers) but sorely lacking in networking phones or notebook computers) but sorely lacking in networking
equipment. equipment.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Basic equipment categorization as "energy-efficient" (or not) as a * Basic equipment categorization as "energy efficient" (or not) as a
first step to identify immediate potential improvements, akin to first step to identify immediate potential improvements, akin to
the EnergyStar program from the US's Environmental Protection the Energy Star program from the US's Environmental Protection
Agency. Agency.
* Equipment instrumentation advances for improved energy-awareness; * Equipment instrumentation advances for improved energy awareness;
definition and standardization of granular management information. definition and standardization of granular management information.
* Virtualized energy and carbon metrics and assessment of their * Virtualized energy and carbon metrics and assessment of their
effectiveness in solutions that optimize carbon footprint also in effectiveness in solutions that optimize carbon footprints in
virtualized environments (including SDN, network slicing, network virtualized environments (including SDN, network slicing, network
function virtualization, etc.). function virtualization, etc.).
* Certification and compliance assessment methods that ensure that * Certification and compliance assessment methods that ensure that
green instrumentation cannot be manipulated to give false and green instrumentation cannot be manipulated to give false and
misleading data. misleading data.
* Methods that allow to account for energy mix powering equipment, * Methods that account for equipment that powers an energy mix, to
to facilitate solutions that optimize carbon footprint and facilitate solutions that optimize carbon footprint and minimize
minimize pollution beyond mere energy efficiency [Hossain2019]. pollution beyond mere energy efficiency [Hossain2019].
5. Challenges and Opportunities - Protocol Level 5. Challenges and Opportunities - Protocol Level
There are several opportunities to improve network sustainability at There are several opportunities to improve network sustainability at
the protocol level. We characterize them along several categories. the protocol level, which can be categorized as follows. The first
The first and arguably most impactful category concerns protocols and arguably most impactful category concerns protocols that enable
that enable carbon footprint optimization schemes at the network carbon footprint optimization schemes at the network level and
level and management towards those goals. Other categories concern management towards those goals. Other categories concern protocols
protocols designed to optimize data transmission rates under energy designed to optimize data transmission rates under energy
considerations, protocols designed to reduce the volume of data to be considerations, protocols designed to reduce the volume of data to be
transmitted, and protocol aspects related to network addressing transmitted, and protocol aspects related to network addressing
schemes. While those categories may be less impactful, even areas schemes. While those categories may be less impactful, even areas
with smaller gains should not be left unexplored. with smaller gains should be explored.
There is also substantial work in the area of IoT, which has had to There is also substantial work in the area of IoT, which has had to
contend with energy-constrained devices for a long time. Much of contend with energy-constrained devices for a long time. Much of
that work was motivated not by sustainability concerns but practical that work was motivated not by sustainability concerns but practical
concerns such as battery life. However, many aspects appear to also concerns such as battery life. However, many aspects appear to also
apply in the context of sustainability, such as reducing chattiness apply in the context of sustainability, such as reducing chattiness
to allow IoT equipment to go into low-power mode. Accordingly, there to allow IoT equipment to go into low-power mode. Accordingly, there
is opportunity to extend IoT work to more generalized scenarios. The is an opportunity to extend IoT work to more generalized scenarios.
use of power-constrained protocols into the wider Internet happens The use of power-constrained protocols in the wider Internet happens
regularly. For instance, ARM-based chipsets initially designed for regularly. For instance, ARM-based chipsets initially designed for
energy-efficiency in battery-operated mobile devices have been energy efficiency in battery-operated mobile devices have been
embraced in data centers for a similar trajectory. embraced in data centers for a similar trajectory.
5.1. Protocol Enablers for Carbon Optimization Mechanisms 5.1. Protocol Enablers for Carbon Optimization Mechanisms
As will be discussed in Section 6, energy-aware and pollution-aware As discussed in Section 6, energy-aware and pollution-aware schemes
schemes can help improve network sustainability but require awareness can help improve network sustainability but require awareness of
of related data. To facilitate such schemes, protocols are needed related data. To facilitate such schemes, protocols are needed that
that are able to discover what links are available along with their are able to discover what links are available along with their energy
energy efficiency. For instance, links may be turned off in order to efficiency. For instance, links may be turned off in order to save
save energy and turned back on based upon the elasticity of the energy and turned back on based upon the elasticity of the demand.
demand. Protocols should be devised to discover when this happens, Protocols should be devised to discover when this happens and to have
and to have a view of the topology that is consistent with frequent a dynamic view of the topology that keeps up with frequent updates
topology updates due to power cycling of the network resources. due to power cycling of the network resources.
Also, protocols are required to quickly converge onto an energy- Also, protocols are required to quickly converge onto an energy-
efficient path once a new topology is created by turning links on/ efficient path once a new topology is created by turning links on/
off. Current routing protocols may provide for fast recovery in the off. Current routing protocols may provide for fast recovery in the
case of failure. However, failures are hopefully relatively rare case of failure. However, failures are hopefully relatively rare
events, while we expect an energy efficient network to aggressively events, while we expect an energy-efficient network to aggressively
try to turn off links. There may be synergies with time-variant try to turn off links. There may be synergies with Time-Variant
routing [I.D.draft-ietf-tvr-requirements] that can be explored, in Routing [TVR_REQS] that can be explored, in which the topology varies
which topology varies over time with nodes and links turned on or off over time with nodes and links turned on or off according to a
according to a schedule. There may even be overlaps in use cases, schedule. There may be overlaps in use cases, for example, when
for example in cases where regular changes in the energy mix (and regular changes in the energy mix (and hence carbon footprint) of
hence carbon footprint) of some nodes occur that coincide with the some nodes occur that coincide with the time of day (such as
time of day (such as switching from solar to fossil fuels at night). switching from solar to fossil fuels at night).
Some mechanism is needed to present to the management layer a view of Some mechanism is needed to present to the management layer a view of
the network that identifies opportunities to turn resources off the network that identifies opportunities to turn off resources
(routers/links) while still providing an acceptable level of Quality (e.g., routers or links) while still providing an acceptable level of
of Experience (QoE) to the users. This gets more complex as the Quality of Experience (QoE) to the users. This gets more complex as
level of QoE shifts from the current Best Effort delivery model to the level of QoE shifts from the current best-effort delivery model
more sophisticated mechanisms with, for instance, latency, bandwidth to more sophisticated mechanisms with, for instance, latency,
or reliability guarantees. bandwidth, or reliability guarantees.
Similarly, schemes might be devised in which links across paths with Similarly, schemes might be devised in which links across paths with
a favorable energy mix are preferred over other paths. This implies a favorable energy mix are preferred over other paths. This implies
that the discovery of topology should be able support corresponding that the discovery of topology should be able support corresponding
parameters. More generally speaking, any mechanism that provides parameters. More generally speaking, any mechanism that provides
applications with network visibility is a candidate for applications with network visibility is a candidate for
scrutinization as to whether it should be extended to provide support scrutinization as to whether it should be extended to provide support
for sustainability-related parameters. for sustainability-related parameters.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Protocol advances to enable rapidly taking down, bring back * Protocol advances to enable rapidly taking down, bringing back
online, and discover availability and power saving status of online, and discovering availability and power-saving status of
networking resources while minimizing the need for reconvergence networking resources while minimizing the need for reconvergence
and propagation of state. and propagation of state.
* An assessment of which protocols could be extended with energy- * An assessment of which protocols could be extended with energy-
and sustainability-related parameters in ways that would enable and sustainability-related parameters in ways that would enable
"greener" networking solutions, and exploration of those "greener" networking solutions, and an exploration of those
solutions. solutions.
5.2. Protocol Optimization 5.2. Protocol Optimization
The second category involves designing protocols in such a way that The second category involves designing protocols in such a way that
the rate of transmission is chosen to maximize energy efficiency. the rate of transmission is chosen to maximize energy efficiency.
For example, Traffic Engineering (TE) can be manipulated to impact For example, Traffic Engineering (TE) can be manipulated to impact
the rate adaptation mechanism [Ren2018jordan]. By choosing where to the rate adaptation mechanism [Ren2018jordan]. By choosing where to
send the traffic, TE can artificially congest links so as to trigger send the traffic, TE can artificially congest links so as to trigger
rate adaptation and therefore reduce the total amount of traffic. rate adaptation and therefore reduce the total amount of traffic.
Most TE systems attempt to minimize Maximal Link Utilization (MLU) Most TE systems attempt to minimize Maximum Link Utilization but
but energy saving mechanisms could decide to do the opposite energy-saving mechanisms could decide to do the opposite (i.e.,
(maximize minimal link utilization) and attempt to turn off some maximize Minimum Link Utilization) and attempt to turn off some
resources to save power. resources to save power.
Another example is to set up the proper rate of transmission to Another example is to set up the proper rate of transmission to
minimize the flow completion time (FCT) so as to enable opportunities minimize the flow completion time (FCT) so as to enable opportunities
to turn off links. In a wireless context, [TradeOff] studies how to turn off links. In a wireless context, [TradeOff] studies how
setting the proper initial value for the congestion window can reduce setting the proper initial value for the congestion window can reduce
the FCT and therefore allow the equipment to go faster into a low- the FCT and therefore allow the equipment to go faster into a low-
energy mode. By sending the data faster, the energy cost can be energy mode. By sending the data faster, the energy cost can be
significantly reduced. This is a simple proof of concept, but significantly reduced. This is a simple proof of concept, but
protocols that allow for turning links into a low-power mode by protocols that allow for turning links into a low-power mode by
transmitting the data over shorter periods could be designed for transmitting the data over shorter periods could be designed for
other types of networks beyond Wi-Fi access. This should be done other types of networks beyond Wi-Fi access. This should be done
carefully: in the limit, a high rate of transmission over a short carefully: in an extreme case, a high rate of transmission over a
period of time may create bursts that the network would need to short period of time may create bursts that the network would need to
accommodate, with all attendant complications of bursty traffic. We accommodate, with all attendant complications of bursty traffic. We
conjecture there is a sweet spot between trying to complete flows conjecture there is a sweet spot between trying to complete flows
faster while controlling for burstiness in the network. It is faster while controlling for burstiness in the network. It is
probably advisable to attempt to send traffic paced yet in bulk probably advisable to attempt to send traffic paced yet in bulk
rather than spread out over multiple round trips. This is an area of rather than spread out over multiple round trips. This is an area of
worthwhile exploration. worthwhile exploration.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Protocol advances that allow greater control over traffic pacing * Protocol advances that allow greater control over traffic pacing
to account for fluctuations in carbon cost, i.e., control knobs to to account for fluctuations in carbon cost, i.e., control knobs to
"bulk up" transmission over short periods or to smoothen it out "bulk up" transmission over short periods or to smooth it out over
over longer periods. longer periods.
* Protocol advances that allow to optimize link utilization * Protocol advances for optimizing link utilization according to
according to different goals and strategies (including maximizing different goals and strategies (including maximizing Minimal Link
minimal link utilization vs minimizing maximal link utilization, Utilization vs. minimizing Maximal Link Utilization, etc.)
etc.)
* Assessments of the carbon impact of such strategies. * Assessments of the carbon impact of such strategies.
5.3. Data Volume Reduction 5.3. Data Volume Reduction
The first category involves designing protocols in such a way that The third category involves designing protocols in such a way that
they reduce the volume of data that needs to be transmitted for any they reduce the volume of data that needs to be transmitted for any
given purpose. Loosely speaking, by reducing this volume, more given purpose. Loosely speaking, by reducing this volume, more
traffic can be served by the same amount of networking traffic can be served by the same amount of networking
infrastructure, hence reducing overall energy consumption. infrastructure, hence reducing overall energy consumption.
Possibilities here include protocols that avoid unnecessary Possibilities here include protocols that avoid unnecessary
retransmissions. At the application layer, protocols may also use retransmissions. At the application layer, protocols may also use
coding mechanisms that encode information close to the Shannon limit. coding mechanisms that encode information close to the Shannon limit.
Currently, most of the traffic over the Internet consists of video Currently, most of the traffic over the Internet consists of video
streaming and encoders for video are already quite efficient and keep streaming, and video encoders are already quite efficient and keep
improving all the time, resulting in energy savings as one of many improving all the time. This results in energy savings as one of
advantages (of course being offset by increasingly higher many advantages, although of course the savings are offset by
resolution). However, it is not clear that the extra work to achieve increasingly higher resolution. It is not clear that the extra work
higher compression ratios for the payloads results in a net energy to achieve higher compression ratios for the payloads results in a
gain: what is saved over the network may be offset by the net energy gain: what is saved over the network may be offset by the
compression/decompression effort. Further research on this aspect is compression/decompression effort. Further research on this aspect is
necessary. necessary.
At the transport protocol layer, TCP and to some extent QUIC react to At the transport protocol layer, TCP and to some extent QUIC react to
congestion by dropping packets. This is a highly energy inefficient congestion by dropping packets. This is an extremely energy
method to signal congestion, since the network has to wait one RTT to inefficient method to signal congestion because (a) the network has
be aware that the congestion has occurred, and since the effort to to wait one RTT to be aware that the congestion has occurred, and (b)
transmit the packet from the source up until it is dropped ends up the effort to transmit the packet from the source up until it is
being wasted. This calls for new transport protocols that react to dropped ends up being wasted. This calls for new transport protocols
congestion without dropping packets. ECN [RFC2481] is a possible that react to congestion without dropping packets. ECN [RFC2481] is
solution, however, it is not widely deployed. DC-TCP a possible solution, however, it is not widely deployed. DCTCP
[Alizadeh2010DCTCP] is tuned for data centers; Low Latency, Low Loss,
[Alizadeh2010DCTCP] is tuned for Data Centers, L4S is an attempt to and Scalable Throughput (L4S) is an attempt to port similar
port similar functionality to the Internet [RFC9330]. Qualitative functionality to the Internet [RFC9330]. Qualitative Communication
Communication [QUAL] [Westphal2021qualitative] allows the nodes to [QUAL] [Westphal2021qualitative] allows the nodes to react to
react to congestion by dropping only some of the data in the packet, congestion by dropping only some of the data in the packet, thereby
thereby only partially wasting the resource consumed by transmitted only partially wasting the resource consumed by transmitted the
the packet up to this point. Novel transport protocols for the WAN packet up to that point. Novel transport protocols for the WAN can
can ensure that no energy is wasted transmitting packets that will be ensure that no energy is wasted transmitting packets that will be
eventually dropped. eventually dropped.
Another solution to reduce the bandwidth of network protocols by Another solution to reduce the bandwidth of network protocols is by
reducing their header tax, for example applying header compression. reducing their header tax, for example, by applying header
An example in IETF is [RFC3095]. Again, reducing protocol header compression. An example in IETF is RObust Header Compression (ROHC)
size saves energy to forward packets, but at the cost of maintaining [RFC3095]. Again, reducing protocol header size saves energy to
a state for compression/decompression, plus computing these forward packets, but at the cost of maintaining a state for
operations. The gain from such protocol optimization further depends compression/decompression, plus computing these operations. The gain
on the application and whether it sends packets with large payloads from such protocol optimization further depends on the application
close to the MTU (the header tax and any savings here are very and whether it sends packets with (a) large payloads close to the
limited), or whether it sends packets with very small payload size MTU, thus limiting the header tax and any savings, or (b) very small
(making the header tax more pronounced and savings more significant). payload size, thus increasing the header tax and the savings.
An alternative to reducing the amount of protocol data is to design An alternative to reducing the amount of protocol data is to design
routing protocols that are more efficient to process at each node. routing protocols that are more efficient to process at each node.
For instance, path-based forwarding/labels such as MPLS [RFC3031] For instance, path-based forwarding/labels such as MPLS [RFC3031]
facilitate the next hop look-up, thereby reducing the energy facilitate the next hop lookup, thereby reducing the energy
consumption. It is unclear if some state at router to speed up look consumption. It is unclear if some state at router to speed up
up is more energy efficient that "no state + lookup" that is more lookup is more energy efficient than "no state + lookup", which is
computationally intensive. Other methods to speed up a next-hop more computationally intensive. Other methods to speed up a next-hop
lookup include geographic routing (e.g., [Herzen2011PIE]). Some lookup include geographic routing (e.g., [Herzen2011PIE]). Some
network protocols could be designed to reduce the next hop look-up network protocols could be designed to reduce the next hop lookup
computation at a router. It is unclear if Longest Prefix Match (LPM) computation at a router. It is unclear whether Longest Prefix Match
is efficient from an energy point of view or if constitutes a (LPM) is energy efficient or a significant energy burden for router
significant energy burden for the operation of a router. operation.
Beyond the volume of data itself, another consideration is the number Beyond the volume of data itself, another consideration is the number
of messages and chattiness of the protocol. Some protocols rely on of messages and chattiness of the protocol. Some protocols rely on
frequent periodic updates or heartbeats, which may prevent equipment frequent periodic updates or heartbeats, which may prevent equipment
to go into sleep mode. In such cases, it makes sense to explore the from going into sleep mode. In such cases, it makes sense to explore
use of feasible alternatives that rely on different communication the use of feasible alternatives that rely on different communication
patterns and fewer messages. patterns and fewer messages.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Assessments of energy-related tradeoffs regarding protocol design * Assessments of energy-related trade-offs regarding protocol design
space and tradeoffs, such as maintaining state versus more compact space and trade-offs, such as maintaining state versus more
encodings or extra computation for transcoding operations versus compact encodings, or extra computation for transcoding operations
larger data volume. versus larger data volume.
* Protocol advances for improving the ratio of goodput to throughput * Protocol advances for improving the ratio of goodput to throughput
and to reduce waste: reduction in header tax, in protocol and to reduce waste: reduction in header tax, in protocol
verbosity, in need for retransmissions, improvements in coding, verbosity, in need for retransmissions, improvements in coding,
etc. etc.
* Protocols that allow to manage transmission patterns in ways that * Protocols that allow for managing transmission patterns in ways
facilitate periods of link inactivity, such as burstiness and that facilitate periods of link inactivity, such as burstiness and
chattiness. chattiness.
5.4. Network Addressing 5.4. Network Addressing
There may be other ways to shave off energy usage from networks. One Network addressing is another way to shave off energy usage from
example concerns network addressing. Address tables can get very networks. Address tables can get very large, resulting in large
large, resulting in large forwarding tables that require considerable forwarding tables that require considerable amount of memory, in
amount of memory, in addition to large amounts of state needing to be addition to large amounts of state that needs to be maintained and
maintained and synchronized. From an energy footprint perspective, synchronized. From an energy footprint perspective, both can be
both can be considered wasteful and offer opportunities for considered wasteful and offer opportunities for improvement. At the
improvement. At the protocol level, rethinking how addresses are protocol level, rethinking how addresses are structured can allow for
structured can allow for flexible addressing schemes that can be flexible addressing schemes that can be exploited in network
exploited in network deployments that are less energy-intensive by deployments that are less energy-intensive by design. This can be
design. This can be complemented by supporting clever address complemented by supporting clever address allocation schemes that
allocation schemes that minimize the number of required forwarding minimize the number of required forwarding entries as part of
entries as part of deployments. deployments.
Alternatively, the address could be designed to allow for more Alternatively, the addressing could be designed to allow for more
efficient processing than LPM. For instance, a geographic type of efficient processing than LPM. For instance, a geographic type of
addressing (where the next hop is computed as a simple distance addressing (where the next hop is computed as a simple distance
calculation based on the respective position of the current node, of calculation based on the respective position of the current node, of
its neighbors and of the destination) [Herzen2011PIE] could be its neighbors and of the destination) [Herzen2011PIE] could be
potentially more energy efficient. potentially more energy efficient.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Devise methods to assess the magnitude of the carbon footprint * Devise methods to assess the magnitude of the carbon footprint
skipping to change at page 21, line 4 skipping to change at line 937
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Devise methods to assess the magnitude of the carbon footprint * Devise methods to assess the magnitude of the carbon footprint
that is associated with addressing schemes. that is associated with addressing schemes.
* Devise methods to improve addressing schemes, as well as address * Devise methods to improve addressing schemes, as well as address
assignment schemes, to minimize their footprint. assignment schemes, to minimize their footprint.
6. Challenges and Opportunities - Network Level 6. Challenges and Opportunities - Network Level
6.1. Network Optimization and Energy/Carbon/Pollution-Aware Networking 6.1. Network Optimization and Energy/Carbon/Pollution-Aware Networking
Networks have been optimized for many years under many criteria, for Networks have been optimized for many years under many criteria, for
example to optimize (maximize) network utilization and to optimize example, to optimize (maximize) network utilization and to optimize
(minimize) cost. Hence, it is straightforward to add optimization (minimize) cost. Hence, it is straightforward to add optimization
for "greenness" (including energy efficiency, power consumption, for "greenness" (including energy efficiency, power consumption,
carbon footprint) as important criteria. carbon footprint) as important criteria.
This includes assessing the carbon footprints of paths and optimizing This includes assessing the carbon footprints of paths and optimizing
those paths so that overall footprint is minimized, then applying those paths so that overall footprint is minimized, then applying
techniques such as path-aware networking or segment routing [RFC8402] techniques such as path-aware networking or segment routing [RFC8402]
to steer traffic along those paths. (As mentioned earlier, other to steer traffic along those paths. (As mentioned earlier, other
proxy measures could be used for carbon footprint, such as an energy- proxy measures could be used for carbon footprint, such as energy-
efficiency ratings of traversed equipment.) It also includes aspects efficiency ratings of traversed equipment.) It also includes aspects
such as considering the incremental carbon footprint in routing such as considering the incremental carbon footprint in routing
decisions. Optimizing cost has a long tradition in networking; many decisions. Optimizing cost has a long tradition in networking; many
of the existing mechanisms can be leveraged for greener networking of the existing mechanisms can be leveraged for greener networking
simply by introducing carbon footprint as a cost factor. Low-hanging simply by introducing the carbon footprint as a cost factor. Low-
fruit include the inclusion of carbon-related parameters as a cost hanging fruit includes adding carbon-related parameters as a cost
parameter in control planes, whether distributed (e.g., IGP) or parameter in control planes, whether distributed (e.g., IGP) or
conceptually centralized via SDN controllers. Likewise, there are conceptually centralized via SDN controllers. Likewise, there are
opportunities in right-placing functionality in the network. An opportunities in right-placing functionality in the network. An
example concerns placement of virtualized network functions in example is placement of virtualized network functions in carbon-
carbon-optimized ways - for example, cohosted on fewer servers in optimized ways, i.e., cohosted on fewer servers in close proximity to
close proximity to each other in order to avoid unnecessary overhead each other in order to avoid unnecessary overhead in long-distance
in long-distance control traffic. control traffic.
Other opportunities concern adding carbon-awareness to dynamic path Other opportunities concern adding carbon awareness to dynamic path
selection schemes. This is sometimes also referred to as "energy- selection schemes. This is sometimes referred to as "energy-aware
aware networking" (respectively "pollution-aware networking" networking" (or "pollution-aware networking" [Hossain2019] or
[Hossain2019] or "carbon-aware networking", when carbon footprint "carbon-aware networking", when parameters beyond simply energy
related parameters beyond pure energy consumption are taken into consumption are taken into account). Again, considerable energy
account). Again, considerable energy savings can potentially be savings can potentially be realized by taking resources offline
realized by taking resources offline (e.g., putting them into power- (e.g., putting them into power-saving or hibernation mode) when they
saving or hibernation mode) when they are not currently needed under are not needed under current network demand and load conditions.
current network demand and load conditions. Therefore, weaning such Therefore, weaning such resources from traffic becomes an important
resources from traffic becomes an important consideration for energy- consideration for energy-efficient traffic steering. This contrasts
efficient traffic steering. This contrasts and indeed conflicts with and indeed conflicts with existing schemes that typically aim to
existing schemes that typically aim to create redundancy and load- create redundancy and load-balance traffic across a network to
balance traffic across a network to achieve even resource achieve even resource utilization. This usually occurs for important
utilization. This usually occurs for important reasons, such as reasons, such as making networks more resilient, optimizing service
making networks more resilient, optimizing service levels, and levels, and increasing fairness. Thus, a big challenge is how
increasing fairness. One of the big challenges hence concerns how resource-weaning schemes to realize energy savings can be
resource weaning schemes to realize energy savings can be accommodated without cannibalizing other important goals,
accommodated while preventing the cannibalization of other important counteracting other established mechanisms, or destabilizing the
goals, counteracting other established mechanisms, and avoiding network.
destabilization of the network.
An opportunity may lie in making a distinction between "energy modes" An opportunity may lie in making a distinction between "energy modes"
of different domains. For instance, in a highly trafficked core, the of different domains. For instance, in a highly trafficked core, the
energy challenge is to transmit the traffic efficiently. The amount energy challenge is to transmit the traffic efficiently. The amount
of traffic is relatively fluid (due to multiplexing of multiple of traffic is relatively fluid (due to multiplexing of multiple
sessions) and the traffic is predictable. In this case, there is no sessions) and the traffic is predictable. In this case, there is no
need to optimize on a per session basis nor even at a short time need to optimize on a per-session basis or at a short timescale. In
scale. In the access networks connecting to that core, though, there the access networks connecting to that core, though, there are
are opportunities for this fast convergence: traffic is much more opportunities for this fast convergence: traffic is much more bursty
bursty, less predictable and the network should be able to be more and less predictable, and the network should be able to be more
reactive. Other domains such as DCs may have also more variable reactive. Other domains such as DCs may have more variable workloads
workloads and different traffic patterns. and different traffic patterns.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Devise methods for carbon-aware traffic steering and routing; * Devise methods for carbon-aware traffic steering and routing;
treat carbon footprint as a traffic cost metric to optimize. treat carbon footprint as a traffic cost metric to optimize.
* Apply ML and AI methods to optimize networks for carbon footprint; * Apply Machine Learning (ML) and AI methods to optimize networks
assess applicability of game theoretic approaches. for carbon footprint; assess applicability of game theoretic
approaches.
* Articulate and, as applicable, moderate tradeoffs between carbon * Articulate and, as applicable, moderate trade-offs between carbon
awareness and other operational goals such as robustness and awareness and other operational goals such as robustness and
redundancy. redundancy.
* Extend control-plane protocols with carbon-related parameters. * Extend control plane protocols with carbon-related parameters.
* Consider security issues imposed by greater energy awareness, to * Consider security issues imposed by greater energy awareness, to
minimize the new attack surfaces that would allow an adversary to minimize the new attack surfaces that would allow an adversary to
turn off resources or to waste energy. turn off resources or to waste energy.
6.2. Assessing Carbon Footprint and Network-Level Instrumentation 6.2. Assessing Carbon Footprint and Network-Level Instrumentation
As an important prerequisite to capture many of the opportunities As an important prerequisite to capture many of the opportunities
outlined in Section 6.1, good abstractions (and corresponding outlined in Section 6.1, good abstractions (and corresponding
instrumentation) that allow to easily assess energy cost and carbon instrumentation) for easily assessing energy cost and carbon
footprint will be required. These abstractions need to account for footprint will be required. These abstractions need to account for
not only for the energy cost associated with packet forwarding across not only the energy cost associated with packet forwarding across a
a given path, but related cost for processing, for memory, for given path, but also the related cost for processing, for memory, and
maintaining of state, to result in a holistic picture. for maintaining of state, to result in a holistic picture.
Optimization of carbon footprint involves in many cases trade-offs In many cases, optimization of carbon footprint has trade-offs that
that involve not only packet forwarding but also aspects such as involve not only packet forwarding but also aspects such as keeping
keeping state, caching data, or running computations at the edge state, caching data, or running computations at the edge instead of
instead of elsewhere. (Note: there may be a differential in running elsewhere. (Note: There may be a differential in running a
a computation at an edge server vs. at an hyperscale DC. The latter computation at an edge server vs. at a hyperscale DC. The latter is
is often better optimized than the latter.) Likewise, other aspects often better optimized than the latter.) Likewise, other aspects of
of carbon footprint beyond mere energy-intensity should be carbon footprint beyond mere energy-intensity should be considered.
considered. For instance, some network segments may be powered by For instance, some network segments may be powered by more
more sustainable energy sources than others, and some network sustainable energy sources than others, and some network equipment
equipment may be more environmentally friendly to build, deploy and may be more environmentally friendly to build, deploy, and recycle,
recycle, all of which can be reflected in abstractions to consider. all of which can be reflected in abstractions to consider.
Assessing carbon footprint at the network level requires Assessing carbon footprint at the network level requires
instrumentation that associates that footprint not just with instrumentation that associates that footprint not just with
individual devices (as outline in Section 4.2 but relates it also to individual devices (as outlined in Section 4.2) but also with
concepts that are meaningful at the network level, i.e., to flows and concepts that are meaningful at the network level, i.e., to flows and
to paths. For example, it will be useful to provide visibility into to paths. For example, it will be useful to provide visibility into
the carbon intensity of a path: Can the carbon cost of traffic the carbon intensity of a path: Can the carbon cost of traffic
transmitted over the path be aggregated? Does the path include transmitted over the path be aggregated? Does the path include
outliers, i.e., segments with equipment with a particularly poor outliers, i.e., segments with equipment with a particularly poor
carbon footprint? carbon footprint?
Similarly, how can the carbon cost of a flow be assessed? That might Similarly, how can the carbon cost of a flow be assessed? That might
serve many purposes beyond network optimization, from the option to serve many purposes beyond network optimization, e.g., introducing
introduce green billing and charging schemes to the ability to raise green billing and charging schemes, and raising carbon awareness by
carbon awareness by end users. end users.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Devise methods to assess, to estimate, to predict carbon-intensity * Devise methods to assess, estimate, and predict the carbon
of paths. intensity of paths.
* Devise methods to account for carbon footprint of flows and * Devise methods to account for the carbon footprint of flows and
networking services. networking services.
6.3. Dimensioning and Peak Shaving 6.3. Dimensioning and Peak Shaving
As mentioned in Section 3, the overall energy usage of a network is As mentioned in Section 3, the overall energy usage of a network is
in large part determined by how the network is dimensioned, in large part determined by how the network is dimensioned,
specifically: which and how many pieces of network equipment are specifically: which and how many pieces of network equipment are
deployed and turned on. A significant portion of energy is drawn deployed and turned on. A significant portion of energy is drawn
even when simply in idle state. Minimizing the amount of equipment even when simply in idle state. Hence, minimizing the amount of
that needs to be turned on in the first place presents hence one of equipment that needs to be turned on in the first place presents one
the biggest energy saving opportunities. of the biggest energy-saving opportunities.
Network deployments are generally dimensioned for periods of peak Network deployments are generally dimensioned for periods of peak
traffic, resulting in excess capacity during periods of non-peak traffic, resulting in excess capacity during periods of non-peak
usage that nonetheless consumes power. Shaving peak usage may thus usage that nonetheless consumes power. Shaving peak usage may thus
result in outsized sustainability gains, as it reduces not only result in outsized sustainability gains, as it reduces energy usage
energy usage during peak traffic, but more importantly waste during during peak traffic but, more importantly, waste during non-peak
non-peak periods. periods.
While traffic volume is largely a function of demand traffic that While traffic volume is largely a function of demand traffic that
network providers have little influence over, some peak shaving cand network providers have little influence over, some peak shaving can
nevertheless be accomplished by techniques such as spreading spikes nevertheless be accomplished by techniques such as spreading spikes
out over geographies (e.g. redirecting some traffic across more out over geographies (e.g., redirecting some traffic across more
costly but less utilized routes, particular in cases when traffic costly but less utilized routes, particularly in cases when traffic
spikes are of a more local or reginal nature) or over time (e.g. spikes are of a more local or regional nature) or over time (e.g.,
postponing non-urgent traffic, storing or buffering using edge clouds postponing non-urgent traffic, storing or buffering using edge clouds
or extra storage where feasible). or extra storage where feasible).
To make techniques effective, accurate learning and prediction of To make techniques effective, accurate learning and prediction of
traffic patterns is required. This includes the ability to perform traffic patterns are required. This includes the ability to perform
forecasting to ensure that additional resources can be spun up in forecasting to ensure that additional resources can be spun up in
time should it be needed. Clearly, this presents interesting time should they be needed. Clearly, this presents interesting
challenges, yet also opportunities for technical advances to make a challenges, yet also opportunities for technical advances to make a
difference. difference.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Support for methods that allow to monitor and forecast traffic * Support methods for monitoring and forecasting traffic demand,
demand, involving new mechanisms and/or performance improvements involving new mechanisms and/or performance improvements of
of existing mechanisms to support the collection of telemetry and existing mechanisms to support the collection of telemetry and
generation of traffic matrices at very high velocity and scale generation of traffic matrices at very high velocity and scale.
* Additional methods that allow for even traffic load distribution * Additional methods for distributing traffic load evenly across the
across the network, i.e. load balancing on a network scale, and network, i.e., load balancing on a network scale, and enablement
enablement of those methods through control protocol extensions as of those methods through control protocol extensions as needed.
needed.
6.4. Convergence Schemes 6.4. Convergence Schemes
One set of challenges of carbon-aware networking concerns the fact One set of challenges of carbon-aware networking concerns the fact
that many schemes result in much greater dynamicity and continuous that many schemes result in much greater dynamicity and continuous
change in the network as resources may be getting steered away from change in the network, as resources may be steered away from (when
(when possible) and then leveraged again (when necessary) in rapid possible) and then leveraged again (when necessary) in rapid
succession. This imposes significant stress on convergence schemes succession. This imposes significant stress on convergence schemes
that results in challenges to the scalability of solutions and their that results in challenges to the scalability of solutions and their
ability to perform in a fast-enough manner. Network-wide convergence ability to perform in a fast-enough manner. Network-wide convergence
imposes high cost and incurs significant delay and is hence not imposes high cost and incurs significant delay and thus is not
susceptible to such schemes. In order to mitigate this problem, susceptible to such schemes. In order to mitigate this problem,
mechanisms should be investigated that do not require convergence mechanisms should be investigated that do not require convergence
beyond the vicinity of the affected network device. Especially in beyond the vicinity of the affected network device. The impact of
cases where central network controllers are involved that are churn needs to be minimized, especially in cases where central
responsible for aspects such as configuration of paths and the network controllers (responsible for the configuration of paths and
positioning of network functions and that aim for global the positioning of network functions and that aim for global
optimization, the impact of churn needs to be minimized. This means optimization) are involved. This means that, for example, discovery,
that, for example, (re-) discovery and update schemes need to be rediscovery, and update schemes need to be simplified, and extensive
simplified and extensive recalculation e.g., of routes and paths recalculation (e.g., of routes and paths based on the current energy
based on the current energy state of the network needs to be avoided. state of the network) needs to be avoided.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Protocols that facilitate rapid convergence (per Section 5.1). * Protocols that facilitate rapid convergence (per Section 5.1).
* Investigate methods that mitigate effects of churn, including * Investigate methods that mitigate effects of churn, including
methods that maintain memory or state as well as methods relying methods that maintain memory or state as well as methods relying
on prediction, inference, and interpolation. on prediction, inference, and interpolation.
6.5. The Role of Topology 6.5. The Role of Topology
One of the most important network management constructs is that of One of the most important network management constructs is that of
the network topology. A network topology can usually be represented the network topology. A network topology can usually be represented
as a database or as a mathematical graph, with vertices or nodes, as a database or as a mathematical graph, with vertices or nodes,
edges or links, representing networking nodes, links connecting their edges or links, representing networking nodes, links connecting their
interfaces, and all their characteristics. Examples of these network interfaces, and all their characteristics. Examples of these network
topology representations include routing protocols link-state topology representations include routing protocols' link-state
databases, and service function chaining graphs. databases (LSDBs) and service function chaining graphs.
As we desire to add carbon and energy awareness into networks, the To add carbon and energy awareness into networks, the energy
energy proportionality of topologies directly supports sustainability proportionality of topologies directly supports visibility into
visibility and improvements via automation. energy consumption and improvements via automation.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Embedding carbon and energy awareness into the representation of * Embedding carbon and energy awareness into the representation of
topologies, whether considering IGP LSDBs (link-state databases) topologies, whether considering IGP LSDBs and their
and their advertisements, BGP-LS (BGP Link-State), or metadata for advertisements, BGP-LS (BGP Link-State), or metadata for the
the rendering of service function paths in a service chain. rendering of service function paths in a service chain.
* Use of those carbon-aware attributes to optimize topology as a * Use of those carbon-aware attributes to optimize topology as a
whole under end-to-end energy and carbon considerations. whole under end-to-end energy and carbon considerations.
7. Challenges and Opportunities - Architecture Level 7. Challenges and Opportunities - Architecture Level
Another possibility to improve network energy efficiency is to Another possibility to improve network energy efficiency is to
organize networks in a way that they allow important applications to organize networks in a way that they allow important applications to
reduce energy consumption. Examples include facilitating retrieval reduce energy consumption. Examples include facilitating retrieval
of content or performing computation in ways that minimize the amount of content or performing computation in ways that minimize the amount
of communication that needs to take place in the first place, even if of communication needed in the first place, even if energy savings
energy savings within the network may at least in part be offset by within the network may be offset (at least in part) by additional
additional energy consumption elsewhere. The following are some energy consumption elsewhere. The following examples suggest that it
examples that suggest that it may be worthwhile reconsidering the may be worthwhile to reconsider the ways in which networks are
ways in which networks are architected to minimize their carbon architected to minimize their carbon footprint.
footprint.
For example, Content Delivery Networks (CDNs) have reduced the energy For example, Content Delivery Networks (CDNs) have reduced the energy
expenditure of the Internet by downloading content near the users. expenditure of the Internet by downloading content near the users.
The content is sent only a few times over the WAN, and then is served The content is sent only a few times over the WAN and then is served
locally. This shifts the energy consumption from networking to locally. This shifts the energy consumption from networking to
storage. Further methods can reduce the energy usage even more storage. Further methods can reduce the energy usage even more
[Bianco2016energy] [Mathew2011energy] [Islam2012evaluating]. Whether [Bianco2016energy] [Mathew2011energy] [Islam2012evaluating]. Whether
overall energy savings are net positive depends on the actual overall energy savings are net positive depends on the actual
deployment, but from the network operator's perspective, at least it deployment, but from the network operator's perspective, at least it
shifts the energy bill away from the network to the CDN operator. shifts the energy bill away from the network to the CDN operator.
While CDNs operate as an overlay, another architecture has been While CDNs operate as an overlay, another architecture has been
proposed to provide the CDN features directly in the network, namely proposed to provide the CDN features directly in the network --
Information Centric Networks [Ahlgren2012survey], studied as well in namely, Information-Centric Networks [Ahlgren2012survey], also
the IRTF ICNRG. This however shifts the energy consumption back to studied in the ICNRG of the IRTF. However, this shifts the energy
the network operator and requires some power-hungry hardware, such as consumption back to the network operator and requires some power-
chips for larger name look-ups and memory for the in-network cache. hungry hardware, such as chips for larger name lookups and memory for
As a result, it is unclear if there is an actual energy gain from the the in-network cache. As a result, it is unclear if there is an
dissemination and retrieval of content within in-network caches. actual energy gain from the dissemination and retrieval of content
within in-network caches.
Fog computing and placing intelligence at the edge are other Fog computing and placing intelligence at the edge are other
architectural directions for reducing the amount of energy that is architectural directions for reducing the amount of energy that is
spent on packet forwarding and in the network. There again, the spent on packet forwarding and in the network. There again, the
trade-off is between performing computation in an energy-optimized trade-off is between performing computational tasks (a) in an energy-
data center at very large scale (but requiring transmission of optimized data center at very large scale (but requiring transmission
significant volumes of data across many nodes and long distances) of significant volumes of data across many nodes and long distances)
versus performing computational tasks at the edge where the energy versus (b) at the edge where the energy may not be used as
may not be used as efficiently (less multiplexing of resources and efficiently (less multiplexing of resources and inherently lower
inherently lower efficiency of smaller sites due to their smaller efficiency of smaller sites due to their smaller scale) but the
scale) but the amount of long-distance network traffic and energy amount of long-distance network traffic and energy required for the
required for the network is significantly reduced. Softwarization, network is significantly reduced. Softwarization, containers, and
containers, microservices are direct enablers for such architectures, microservices are direct enablers of such architectures. Their
and the deployment of programmable network infrastructure (as for realization will be further aided by the deployment of programmable
instance Infrastructure Processing Units - IPUs or SmartNICs that network infrastructure, such as Infrastructure Processing Units
offload some computations from the CPU onto the NIC) will help its (IPUs) or SmartNICs that offload some computations from the CPU onto
realization. However, the power consumption characteristics of CPUs the NIC. However, the power consumption characteristics of CPUs are
are different from those of NPUs, another aspect to be considered in different from those of NPUs; this is another aspect to be considered
conjunction with virtualization. in conjunction with virtualization.
Other possibilities concern taking economic aspects into Other possibilities are taking economic aspects into consideration,
consideration impact, such as providing incentives to users of such as providing incentives to users of networking services in order
networking services in order to minimize energy consumption and to minimize energy consumption and emission impact. In
emission impact. An example for this is given in [Wolf2014choicenet], an example is provided that could be expanded to
[Wolf2014choicenet], which could be expanded to include energy include energy incentives.
incentives.
Other approaches consider performing a late binding of data and Other approaches consider performing a late binding of the data and
functions to be performed on the data [Krol2017NFaaS]. The COIN the functions to be performed on it [Krol2017NFaaS]. The COINRG of
Research Group in IRTF focuses on similar issues. Jointly optimizing the IRTF focuses on similar issues. Jointly optimizing for the total
for the total energy cost that takes into account networking as well energy cost that takes into account networking as well as computing
as computing (along with the different energy cost of computing in an (along with the different energy cost of computing in a hyperscale DC
hyperscale DC vs at an edge node) is still an area of open research. vs. at an edge node) is still an area of open research.
In summary, rethinking of the overall network (and networked In summary, rethinking the overall network (and networked
application) architecture can be an opportunity to significantly application) architecture can be an opportunity to significantly
reduce the energy cost at the network layer, for example by reduce the energy cost at the network layer, for example, by
performing tasks that involve massive communications closer to the performing tasks that involve massive communications closer to the
user. To what extend these shifts result in a net reduction of user. To what extent these shifts result in a net reduction of
carbon footprint is an important question that requires further carbon footprint is an important question that requires further
analysis on a case-by-case basis. analysis on a case-by-case basis.
The following summarizes some challenges and opportunities in this The following summarizes some challenges and opportunities in this
space that can provide the basis for advances in greener networking: space that can provide the basis for advances in greener networking:
* Investigate organization of networking architecture for important * Investigate organization of networking architecture for important
classes of applications (examples: content delivery, right-placing classes of applications (e.g., content delivery, right-placing of
of computational intelligence, industrial operations and control, computational intelligence, industrial operations and control,
massively distributed machine learning and AI) to optimize green massively distributed ML and AI) to optimize green footprint and
foot print and holistic approaches to trade off carbon footprint holistic approaches to trade-offs of carbon footprint with
between forwarding, storage, and computation. forwarding, storage, and computation.
* Models to assess and compare alternatives in providing networked * Models to assess and compare alternatives in providing networked
services, e.g., evaluate carbon impact relative to alternatives services, e.g., evaluate carbon impact relative to where to
where to perform compute, what information to cache, and what perform computation, what information to cache, and what
communication exchanges to conduct. communication exchanges to conduct.
8. Conclusions 8. Conclusions
How to make networks "greener" and reduce their carbon footprint is How to make networks "greener" and reduce their carbon footprint is
an important problem for the networking industry to address, both for an important problem for the networking industry to address, both for
societal and for economic reasons. This document has highlighted a societal and for economic reasons. This document has highlighted a
number of the technical challenges and opportunities in that regard. number of the technical challenges and opportunities in that regard.
Of those, perhaps the key challenge to address right away concerns Of those, perhaps the key challenge to address right away is the
the ability to expose at a fine granularity the energy impact of any ability to expose at a fine granularity the energy impact of any
networking actions. Providing visibility into this will enable many networking actions. Providing visibility into this will enable many
approaches to come towards a solution. It will be key to approaches to come towards a solution. It will be key to
implementing optimization via control loops that allow to assess the implementing optimization via control loops that can assess the
energy impact of decision taken. It will also help to answer energy impact of a decision taken. It will also help to answer
questions such as: is caching - with the associated storage energy - questions such as:
better than retransmitting from a different server - with the
associated networking cost? Is compression more energy-efficient * Is caching (with the associated storage) better than
once factoring the computation cost of compression vs transmitting retransmitting from a different server (with the associated
uncompressed data? Which compression scheme is more energy networking cost)?
efficient? Is energy saving of computing at an efficient hyperscale * Is compression more energy efficient once factoring in the
DC compensated by the networking cost to reach that DC? Is the computation cost of compression vs. transmitting uncompressed
overhead of gathering and transmitting fine-grained energy telemetry data?
data offset by the total energy gain by ways of better decisions that * Which compression scheme is more energy efficient?
this data enables? Is transmitting data to a Low Earth Orbit (LEO) * Is energy saving of computing at an efficient hyperscale DC
satellite constellation compensated by the fact that once in the compensated by the networking cost to reach that DC?
constellation, the networking is fueled by solar energy? Is the * Is the overhead of gathering and transmitting fine-grained energy
energy cost of sending rockets to place routers in Low Earth Orbit telemetry data offset by the total energy gain resulting from the
amortized over time? better decisions that this data enables?
* Is transmitting data to a Low Earth Orbit (LEO) satellite
constellation compensated by the fact that once in the
constellation, the networking is fueled by solar energy?
* Is the energy cost of sending rockets to place routers in LEO
amortized over time?
Determining where the sweet spots are and optimizing networks along Determining where the sweet spots are and optimizing networks along
those lines will be a key towards making networks "greener". We those lines will be a key towards making networks "greener". We
expect to see significant advances across these areas and believe expect to see significant advances across these areas and believe
that researchers, developers, and operators of networking technology that researchers, developers, and operators of networking technology
have an important role to play in this. have an important role to play in this.
9. IANA Considerations 9. IANA Considerations
This document does not have any IANA requests. This document has no IANA actions.
10. Security Considerations 10. Security Considerations
Security considerations may appear to be orthogonal to green Security considerations may appear to be orthogonal to green
networking considerations. However, there are a number of important networking considerations. However, there are a number of important
caveats. caveats.
Security vulnerabilities of networks may manifest themselves in Security vulnerabilities of networks may manifest themselves in
compromised energy efficiency. For example, attackers could aim at compromised energy efficiency. For example, attackers could aim at
increasing energy consumption to drive up attack victims' energy increasing energy consumption to drive up attack victims' energy
bill. Specific vulnerabilities will depend on the particular bills. Specific vulnerabilities will depend on the particular
mechanisms. For example, in the case of monitoring energy mechanisms. For example, in the case of monitoring energy
consumption data, tampering with such data might result in consumption data, tampering with such data might result in
compromised energy optimization control loops. Hence any mechanisms compromised energy optimization control loops. Hence, any mechanisms
to instrument and monitor the network for such data need to be to instrument and monitor the network for such data need to be
properly secured to ensure authenticity. properly secured to ensure authenticity.
In some cases, there are inherent tradeoffs between security and In some cases, there are inherent trade-offs between security and
maximal energy efficiency that might otherwise be achieved. An maximal energy efficiency that might otherwise be achieved. An
example is encryption, which requires additional computation for example is encryption, which requires additional computation for
encryption and decryption activities and security handshakes, in encryption and decryption activities and security handshakes, in
addition to the need to send more traffic than necessitated by the addition to the need to send more traffic than necessitated by the
entropy of the actual data stream. Likewise, mechanisms that allow entropy of the actual data stream. Likewise, mechanisms that allow
to turn resources on or off could become a target for attackers. to turn resources on or off could become a target for attackers.
Energy consumption can be used to create covert channels, which is a Energy consumption can be used to create covert channels, which is a
security risk for information leakage. For instance, the temperature security risk for information leakage. For instance, the temperature
of an element can be used to create a Thermal Covert Channel [TCC], of an element can be used to create a Thermal Covert Channel [TCC],
or the reading/sharing of the measured energy consumption can be or the reading/sharing of the measured energy consumption can be
abused to create a covert channel (see for instance [DRAM] or abused to create a covert channel (see for instance [DRAM] or
[NewClass]). Power information may be used to create side-channel [NewClass]). Power information may be used to create side-channel
attacks. For instance, [SideChannel] provides a review of 20 years attacks. For instance, [SideChannel] provides a review of 20 years
of study on this topic. Any new parameters considered in protocol of study on this topic. Any new parameters considered in protocol
designs or in measurements are susceptible to create such covert or designs or in measurements are susceptible to create such covert or
side channel and this should be taken into account while designing side channels, and this should be taken into account while designing
energy efficient protocols. energy-efficient protocols.
11. Contributors
Michael Welzl, University of Oslo, michawe@ifi.uio.no
12. Acknowledgments
The authors thank Dave Oran for providing the information regarding
covert channels using energy measurements, and Mike King for an
exceptionally thorough review and useful comments.
13. Informative References 11. Informative References
[Ahlgren2012survey] [Ahlgren2012survey]
Ahlgren, B., Dannewitz, C., Imbrenda, C., Kutscher, D., Ahlgren, B., Dannewitz, C., Imbrenda, C., Kutscher, D.,
and B. Ohlman, "A survey of information-centric and B. Ohlman, "A survey of information-centric
networking", IEEE Communications Magazine Vol.50 No.7, networking", IEEE Communications Magazine, vol. 50, no. 7,
2012. pp. 26-36, DOI 10.1109/MCOM.2012.6231276, 2012,
<https://doi.org/10.1109/MCOM.2012.6231276>.
[Alizadeh2010DCTCP] [Alizadeh2010DCTCP]
Alizadeh, M., Greenberg, A., Maltz, D., Padhye, J., Patel, Alizadeh, M., Greenberg, A., Maltz, D., Padhye, J., Patel,
P., Prabhakar, B., Sengupta, S., and M. Sridharan, "Data P., Prabhakar, B., Sengupta, S., and M. Sridharan, "Data
Center TCP (DCTCP)", ACM SIGCOMM pp.63-74, 2010. Center TCP (DCTCP)", ACM SIGCOMM Computer Communication
Review, vol. 40, no. 4, pp. 63-74,
DOI 10.1145/1851275.1851192, 2010,
<https://doi.org/10.1145/1851275.1851192>.
[Bianco2016energy] [Bianco2016energy]
Bianco, A., Mashayekhi, R., and M. Meo, "Energy Bianco, A., Mashayekhi, R., and M. Meo, "Energy
consumption for data distribution in content delivery consumption for data distribution in content delivery
networks", IEEE International Conference on Communications networks", IEEE International Conference on Communications
(ICC) pp.1-6, 2016. (ICC), pp. 1-6, DOI 10.1109/ICC.2016.7511356, 2016,
<https://doi.org/10.1109/ICC.2016.7511356>.
[Bolla2011energy] [Bolla2011energy]
Bolla, R., Bruschi, R., Davoli, F., and F. Cucchietti, Bolla, R., Bruschi, R., Davoli, F., and F. Cucchietti,
"Energy Efficiency in the Future Internet: A Survey of "Energy Efficiency in the Future Internet: A Survey of
Existing Approaches and Trends in Energy-Aware Fixed Existing Approaches and Trends in Energy-Aware Fixed
Network Infrastructures", IEEE Communications Surveys and Network Infrastructures", IEEE Communications Surveys and
Tutorials Vol.13 No.2, pp.223-244, 2011. Tutorials, vol. 13, no. 2, pp. 223-244,
DOI 10.1109/SURV.2011.071410.00073, 2011,
<https://doi.org/10.1109/SURV.2011.071410.00073>.
[Cervero19] [Cervero15]
Cervero, A. G., Chincoli, M., Dittmann, L., Fischer, A., Cervero, A. G., Chincoli, M., Dittmann, L., Fischer, A.,
and A. Garcia, "Green Wired Networks", Wiley Journal on Garcia, A., Galán-Jiménez, J., Lefevre, L., Meer, H. D.,
Large-Scale Distributed Systems and Energy Monteil, T., Monti, P., Orgerie, A., Pau, L., Phillips,
Efficiency pp.41-80, 2019. C., Ricciardi, S., Sharrock, R., Stolf, P., Trinh, T., and
L. Valcarenghi, "Green Wired Networks", Large-Scale
Distributed Systems and Energy Efficiency, pp. 41-80,
DOI 10.1002/9781118981122.ch3, 2015,
<https://doi.org/10.1002/9781118981122.ch3>.
[Chabarek08] [Chabarek08]
Chabarek, J., Sommers, J., Barford, P., Tsiang, D., and S. Chabarek, J., Sommers, J., Barford, P., Estan, C., Tsiang,
Wright, "Power awareness in network design and routing", D., and S. Wright, "Power Awareness in Network Design and
IEEE Infocom pp.457-465, 2008. Routing", IEEE INFOCOM 2008 - The 27th Conference on
Computer Communications, pp. 457-465,
DOI 10.1109/INFOCOM.2008.93, 2008,
<https://doi.org/10.1109/INFOCOM.2008.93>.
[DRAM] Paiva, T. B., Navaridas, J., and R. Terada, "Robust Covert [DRAM] Paiva, T. B., Navaridas, J., and R. Terada, "Robust Covert
Channels Based on DRAM Power Consumption", In book: Channels Based on DRAM Power Consumption", Information
Information Security (pp.319-338) , 2019. Security, ISC 2019, Lecture Notes in Computer Science, vol
11723, DOI 10.1007/978-3-030-30215-3_16, 2019,
<https://doi.org/10.1007/978-3-030-30215-3_16>.
[Emergy] Raghavan, B. and J. Ma, "The Energy and Emergy of the [Emergy] Raghavan, B. and J. Ma, "The Energy and Emergy of the
Internet", ACM HotNets , 2011. Internet", Proceedings of the 10th ACM Workshop on Hot
Topics in Networks, no. 9, pp. 1-6,
DOI 10.1145/2070562.2070571, 2011,
<https://doi.org/10.1145/2070562.2070571>.
[Framework] [Framework]
Faber, G., "A framework to estimate emissions from virtual Faber, G., "A framework to estimate emissions from virtual
conferences", International Journal of Environmental conferences", International Journal of Environmental
Studies, 78:4, 608-623 , 2021. Studies, vol. 78, no. 4, pp. 608-623,
DOI 10.1080/00207233.2020.1864190, 2021,
<https://doi.org/10.1080/00207233.2020.1864190>.
[GreenNet22] [GreenNet22]
Clemm, A. and C. Westphal, "Challenges and Opportunities Clemm, A. and C. Westphal, "Challenges and Opportunities
in Green Networking", 1st International Workshop on in Green Networking", 1st International Workshop on
Network Energy Efficiency in the Softwarization Era IEEE Network Energy Efficiency in the Softwarization Era, IEEE
NetSoft 2022, June 2022. NetSoft 2022, DOI 10.1109/NetSoft54395.2022.9844020, June
2022, <https://doi.org/10.1109/NetSoft54395.2022.9844020>.
[GREEN_METRICS]
Clemm, A., Ed., Pignataro, C., Ed., Schooler, E.,
Ciavaglia, L., Rezaki, A., Mirsky, G., and J. Tantsura,
"Green Networking Metrics for Environmentally Sustainable
Networking", Work in Progress, Internet-Draft, draft-cx-
green-green-metrics-00, 21 October 2024,
<https://datatracker.ietf.org/doc/html/draft-cx-green-
green-metrics-00>.
[Herzen2011PIE] [Herzen2011PIE]
Herzen, J., Westphal, C., and P. Thiran, "Scalable routing Herzen, J., Westphal, C., and P. Thiran, "Scalable routing
easy as PIE: A practical isometric embedding protocol", easy as PIE: A practical isometric embedding protocol",
19th IEEE International Conference on Network Protocols 19th IEEE International Conference on Network Protocols
(ICNP) pp.49-58, 2011. (ICNP), pp. 49-58, DOI 10.1109/ICNP.2011.6089081, 2011,
<https://doi.org/10.1109/ICNP.2011.6089081>.
[Hossain2019] [Hossain2019]
Hossain, M., Georges, J., Rondeau, E., and T. Divoux, Hossain, M., Georges, J., Rondeau, E., and T. Divoux,
"Energy, Carbon and Renewable Energy: Candidate Metrics "Energy, Carbon and Renewable Energy: Candidate Metrics
for Green-Aware Routing?", DOI 10.3390/s19132901, for Green-Aware Routing?", Sensors, vol. 19, no. 3,
Sensors Vol. 19 No. 3, June 2019, DOI 10.3390/s19132901, June 2019,
<https://ieeexplore.ieee.org/document/6779082>. <https://doi.org/10.3390/s19132901>.
[I.D.draft-cx-green-green-metrics]
Clemm, A., Pignataro, C., Schooler, E., Ciavaglia, L.,
Rezaki, A., Mirsky, G., and J. Tantsura, "Green Networking
Metrics", October 2024.
[I.D.draft-ietf-tvr-requirements]
King, D., Contreras, L., Sipos, B., and L. Zhang, "TVR
(Time-Variant Routing) Requirements", September 2024.
[I.D.draft-li-green-power]
Li, T. and R. Bonica, "A YANG model for Power Management",
October 2024.
[IETF-Net0] [IETF-Net0]
Daley, J., "Towards a net zero IETF", IETF News , 6 May Daley, J., "Towards a net zero IETF", IETF News, 6 May
2022, 2022,
<https://www.ietf.org/blog/towards-a-net-zero-ietf/>. <https://www.ietf.org/blog/towards-a-net-zero-ietf/>.
[Islam2012evaluating] [Islam2012evaluating]
Islam, S. U. and J. Pierson, "Evaluating Energy Islam, S. U. and J. Pierson, "Evaluating Energy
Consumption in CDN Servers", Proceedings of the Second Consumption in CDN Servers", Proceedings of the Second
International Conference on ICT as Key Technology against International Conference on ICT as Key Technology against
Global Warming pp.64-78, 2012. Global Warming, Lecture Notes in Computer Science, vol
7453, pp. 64-78, DOI 10.1007/978-3-642-32606-6_6, 2012,
<https://doi.org/10.1007/978-3-642-32606-6_6>.
[Junkyard] Switzer, J., Kastner, R., and P. Pannuto, "Architecture of [Junkyard] Switzer, J., Kastner, R., and P. Pannuto, "Architecture of
a Junkyard Datacenter", arXiv:2110.06870v1, October 2021 , a Junkyard Datacenter", DOI 10.48550/arXiv.2110.06870,
2021. arXiv: 2110.06870v1, 2021,
<https://arxiv.org/abs/2110.06870v1>.
[Krol2017NFaaS] [Krol2017NFaaS]
Krol, M. and I. Psaras, "NFaaS: Named Function as a Krol, M. and I. Psaras, "NFaaS: Named Function as a
Service", ACM SIGCOMM ICN Conference , 2017. Service", ICN '17: Proceedings of the 4th ACM Conference
on Information-Centric Networking, pp. 134-144,
DOI 10.1145/3125719.3125727, 2017,
<https://doi.org/10.1145/3125719.3125727>.
[Mathew2011energy] [Mathew2011energy]
Mathew, V., Sitaraman, R., and P. Shenoy, "Energy-Aware Mathew, V., Sitaraman, R., and P. Shenoy, "Energy-Aware
Load Balancing in Content Delivery Networks", CoRR Load Balancing in Content Delivery Networks",
http://arxiv.org/abs/1109.5641 , 2011. DOI 10.48550/arXiv.1109.5641, arXiv: 1109.5641v1, 2011,
<https://arxiv.org/abs/1109.5641>.
[NewClass] Khatamifard, S. K., Wang, L., Kose, S., and U. R. [NewClass] Khatamifard, S. K., Wang, L., Kose, S., and U. R.
Karpuzcu, "A New Class of Covert Channels Exploiting Power Karpuzcu, "A New Class of Covert Channels Exploiting Power
Management Vulnerabilities", IEEE Computer Architecture Management Vulnerabilities", IEEE Computer Architecture
Letters , 2018. Letters, vol. 15, no. 2, pp. 201-204,
DOI 10.1109/LCA.2018.2860006, 2018,
<https://doi.org/10.1109/LCA.2018.2860006>.
[POWER_YANG]
Li, T. and R. Bonica, "A YANG model for Power Management",
Work in Progress, Internet-Draft, draft-li-green-power-00,
17 October 2024, <https://datatracker.ietf.org/doc/html/
draft-li-green-power-00>.
[QUAL] Li, R., Makhijani, K., Yousefi, H., Westphal, C., Xong, [QUAL] Li, R., Makhijani, K., Yousefi, H., Westphal, C., Xong,
L., Wauters, T., and F. D. Turck, "A Framework for L., Wauters, T., and F. D. Turck, "A Framework for
Qualitative Communications using Big Packet Protocol", Qualitative Communications using Big Packet Protocol",
Proceedings ACM Sigcomm Workshop On Networking For NEAT'19: Proceedings of the ACM Sigcomm Workshop On
Emerging Applications And Technologies pp.22-28, 2019. Networking For Emerging Applications And Technologies, pp.
22-28, DOI 10.1145/3341558.3342201, 2019,
<https://doi.org/10.1145/3341558.3342201>.
[Ren2018jordan] [Ren2018jordan]
Ren, J., Ren, K., Westphal, C., Wang, J., Wang, J., Song, Ren, J., Lu, K., Westphal, C., Wang, J., Wang, J., Song,
T., Liu, S., and J. Wang, "JORDAN: A Novel Traffic T., Liu, S., and J. Wang, "JORDAN: A Novel Traffic
Engineering Algorithm for Dynamic Adaptive Streaming over Engineering Algorithm for Dynamic Adaptive Streaming over
HTTP", IEEE International Conference on Computing, HTTP", 2018 International Conference on Computing,
Networking and Communications (ICNC) pp.581-587, 2018. Networking and Communications (ICNC), pp. 581-587,
DOI 10.1109/ICCNC.2018.8390337, 2018,
<https://doi.org/10.1109/ICCNC.2018.8390337>.
[RFC2481] Ramakrishnan, K. and S. Floyd, "A Proposal to add Explicit [RFC2481] Ramakrishnan, K. and S. Floyd, "A Proposal to add Explicit
Congestion Notification (ECN) to IP", RFC 2481, Congestion Notification (ECN) to IP", RFC 2481,
DOI 10.17487/RFC2481, January 1999, DOI 10.17487/RFC2481, January 1999,
<https://www.rfc-editor.org/info/rfc2481>. <https://www.rfc-editor.org/info/rfc2481>.
[RFC3031] Rosen, E., Viswanathan, A., and R. Callon, "Multiprotocol [RFC3031] Rosen, E., Viswanathan, A., and R. Callon, "Multiprotocol
Label Switching Architecture", RFC 3031, Label Switching Architecture", RFC 3031,
DOI 10.17487/RFC3031, January 2001, DOI 10.17487/RFC3031, January 2001,
<https://www.rfc-editor.org/info/rfc3031>. <https://www.rfc-editor.org/info/rfc3031>.
skipping to change at page 32, line 36 skipping to change at line 1526
[RFC9330] Briscoe, B., Ed., De Schepper, K., Bagnulo, M., and G. [RFC9330] Briscoe, B., Ed., De Schepper, K., Bagnulo, M., and G.
White, "Low Latency, Low Loss, and Scalable Throughput White, "Low Latency, Low Loss, and Scalable Throughput
(L4S) Internet Service: Architecture", RFC 9330, (L4S) Internet Service: Architecture", RFC 9330,
DOI 10.17487/RFC9330, January 2023, DOI 10.17487/RFC9330, January 2023,
<https://www.rfc-editor.org/info/rfc9330>. <https://www.rfc-editor.org/info/rfc9330>.
[SideChannel] [SideChannel]
Randolph, M. and W. Diehl, "Power Side-Channel Attack Randolph, M. and W. Diehl, "Power Side-Channel Attack
Analysis: A Review of 20 Years of Study for the Layman", Analysis: A Review of 20 Years of Study for the Layman",
Cryptography 2020, 4, 15 , 2020. Cryptography, vol. 4, no. 2,
DOI 10.3390/cryptography4020015, 2020,
<https://doi.org/10.3390/cryptography4020015>.
[TCC] Rahimi, P., Singh, A. K., and X. Wang, "Selective Noise [TCC] Rahimi, P., Singh, A. K., and X. Wang, "Selective Noise
Based Power Efficient and Effective Countermeasure Against Based Power-Efficient and Effective Countermeasure Against
Thermal Covert Channel Attacks in Multi-Core Systems", Thermal Covert Channel Attacks in Multi-Core Systems",
Journal on Low Power Electronics and Applications , 2022. Journal on Low Power Electronics and Applications, vol.
12, no. 2, DOI 10.3390/jlpea12020025, 2022,
<https://doi.org/10.3390/jlpea12020025>.
[Telefonica2021] [Telefonica2021]
Telefonica, "Telefonica Consolidated Annual Report 2021.", Telefonica, "Telefonica Consolidated Annual Report 2021",
2021. 2021.
[TradeOff] Welzl, M., "Not a Trade-Off: On the Wi-Fi Energy [TradeOff] Welzl, M., "Not a Trade-Off: On the Wi-Fi Energy
Efficiency of Effective Internet Congestion Control", Efficiency of Effective Internet Congestion Control", 2022
IEEE/IFIP WONS , 2022. 17th Wireless On-Demand Network Systems and Services
Conference (WONS), pp. 1-4,
DOI 10.23919/WONS54113.2022.9764413, 2022,
<https://doi.org/10.23919/WONS54113.2022.9764413>.
[TVR_REQS] King, D., Contreras, L. M., Sipos, B., and L. Zhang, "TVR
(Time-Variant Routing) Requirements", Work in Progress,
Internet-Draft, draft-ietf-tvr-requirements-06, 7 July
2025, <https://datatracker.ietf.org/doc/html/draft-ietf-
tvr-requirements-06>.
[Westphal2021qualitative] [Westphal2021qualitative]
Westphal, C., He, D., Makhijani, K., and R. Li, Westphal, C., He, D., Makhijani, K., and R. Li,
"Qualitative Communications for Augmented Reality and "Qualitative Communications for Augmented Reality and
Virtual Reality", 22nd IEEE International Conference on Virtual Reality", 22nd IEEE International Conference on
High Performance Switching and Routing (HPSR) pp.1-6, High Performance Switching and Routing (HPSR), pp. 1-6,
2021. DOI 10.1109/HPSR52026.2021.9481793, 2021,
<https://doi.org/10.1109/HPSR52026.2021.9481793>.
[Wolf2014choicenet] [Wolf2014choicenet]
Tilman, W., Griffioen, J., Calvert, L., Dutta, R., Tilman, W., Griffioen, J., Calvert, L., Dutta, R.,
Rouskas, G., Baldin, I., and A. Nagurney, "ChoiceNet: Rouskas, G., Baldin, I., and A. Nagurney, "ChoiceNet:
Toward an Economy Plane for the Internet", SIGCOMM Toward an Economy Plane for the Internet", ACM SIGCOMM
Computer Communciations Review Vol.44 No.3, July 2014. Computer Communciations Review, vol. 44, no. 3, pp. 58-65,
DOI 10.1145/2656877.2656886, July 2014,
<https://doi.org/10.1145/2656877.2656886>.
Acknowledgments
The authors thank Dave Oran for providing the information regarding
covert channels using energy measurements and Mike King for an
exceptionally thorough review and useful comments.
Contributors
Michael Welzl
University of Oslo
Email: michawe@ifi.uio.no
Authors' Addresses Authors' Addresses
Alexander Clemm (editor) Alexander Clemm (editor)
Independent Independent
Los Gatos, CA, Los Gatos, CA
United States of America United States of America
Email: ludwig@clemm.org Email: ludwig@clemm.org
Carlos Pignataro (editor) Carlos Pignataro (editor)
North Carolina State University North Carolina State University
United States of America United States of America
Email: cpignata@gmail.com, cmpignat@ncsu.edu Email: cpignata@gmail.com, cmpignat@ncsu.edu
Cedric Westphal Cedric Westphal
Email: westphal@ieee.org Email: westphal@ieee.org
 End of changes. 206 change blocks. 
703 lines changed or deleted 757 lines changed or added

This html diff was produced by rfcdiff 1.48.