It Is Time to Address Network Power Proportionality
OPEN ACCESS
Loading...
Author / Producer
Date
2025-11-17
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
In recent years, networking hardware development has primarily focused on speed rather than power efficiency. By contrast, computing hardware has received a lot more attention given its dominant power footprint, especially in machine-learning (ML) data centers. With faster networks, we spend less time communicating and get more useful work out of the (increasingly expensive) computing hardware. But, the faster the network, the more time it idles and the worse its energy efficiency, which is magnified by the notorious lack of power proportionality of networking equipment. In this paper, we analyze the network power footprint in a production ML cluster and find that it accounts for a still sizeable fraction of the total (12%) and that, by improving network power proportionality to match that of the compute, one could save close to 9% of the overall cluster energy demand. We argue that this potential is worth investigating and discuss opportunities and challenges to address power proportionality in networking hardware, which we invite the networking research community to tackle.
Permanent link
Publication status
published
External links
Editor
Book title
HotNets '25: Proceedings of the 24th ACM Workshop on Hot Topics in Networks
Journal / series
Volume
Pages / Article No.
308 - 316
Publisher
Association for Computing Machinery
Event
24th ACM Workshop on Hot Topics in Networks (HotNets 2025)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Sustainable networking; Power proportionality; Machine learning infrastructure
Organisational unit
09477 - Vanbever, Laurent / Vanbever, Laurent