Category: IT Energy
-
Model, estimate or measure? What matters in video energy use
Analyzing the difference between energy and power estimates from software models vs a hardware analyzer in video communications.
-
Network energy use not directly proportional to data volume
It is commonly assumed that data volume and network energy consumption are directly proportional, a notion perpetuated by numerous studies and media coverage. This paper challenges this assumption.
-
Expect more overestimates of AI energy consumption
We’ve started to see AI doomerism spread to predictions of the vast quantity of energy AI is undoubtably going to consume.
-
Stretched grid? Managing data center energy demand and grid capacity
As more data centers are built, competing with other users like housing projects and electric vehicle (EV) charging, how should the energy system change to accommodate these evolving uses?
-
Paper Notes – ICT sector electricity consumption and greenhouse gas emissions 2020
An updated look at the total electricity consumption and associated GHG emissions for the ICT sector in 2020. Paper notes on Malmodin et al. (2023).
-
Paper Notes – The world wide web of carbon
Will we ever be able to accurately assess the carbon footprint of IT? Could a relational footprint methodology be more useful? Paper notes on Pasek et al (2023).
-
DPhil in Engineering Science
In October 2022 I started a DPhil (PhD) in Engineering Science researching sustainable computing at the University of Oxford.
-
Value judgments and sustainable computing
Puritan value judgments don’t help and any analysis based on concepts of digital sobriety or arbitrary definitions of waste should be rejected.
-
Paper Notes – RAPL In Action
Notes on the paper Khan et al (2018) RAPL in Action: Experiences in Using RAPL for Power Measurements. Advantages and limitations of the Running Average Power Limit (RAPL) interface.
-
Paper notes – Jupiter Evolving: Transforming Google’s Datacenter Network
Removing the aggregation spine resulted in 5x higher speed and capacity, and 41% reduction in power.