This project aims to establish a benchmark for measuring carbon emissions.
“All models are wrong. Some models are useful.”
The goal of this project is to make the carbon emissions model for cloud-based workloads:
- less wrong, by defining a standard mechanism for cloud providers to share more information; and
- more useful, by having the same data schema for all cloud providers, and to support updates to that data in real time, which could be minute level granularity for energy usage, and hourly or daily granularity for carbon intensity.
Cloud providers are the largest purchasers of renewable energy in the world, but so far they have provided their customers with carbon information on a monthly basis, a few months in arrears, so customers have had to produce their own real-time estimates for cloud workloads, using public information that doesn't include those purchases and overestimates carbon footprints. As part of the information technology supply chain, cloud providers need to supply real-time carbon metrics that can be aggregated by workload, allocated and apportioned through the supply chain to satisfy regulations that are in place in the UK and Europe, on the way in California, and emerging elsewhere. Cloud providers build their own custom silicon and systems designs, and optimize them for low power consumption and to reduce the carbon footprint of their supply chain.
Using this standard, the efficiency benefits combined with the renewable energy purchases of cloud providers can be compared directly to datacenter alternatives for specific workloads.
Many software as a service (SaaS) providers run multi-tenant workloads on cloud providers. To supply their own customers with carbon footprint estimates, the instance level energy and carbon data needs to be allocated and attributed across workloads. The Kepler project hosted by the Cloud Native Computing Foundation allocates the energy usage of a host node to the active pods and containers running in that node, so that energy and carbon data can be reported for workloads running on Kubernetes. In datacenter deployments Kepler can directly measure energy usage and obtain carbon intensity data from the datacenter operator. Cloud providers block direct access to energy usage metrics as part of their multi-tenant security model, but could safely provide energy data to Kepler via this standard at one minute intervals.
The initial work is focused on collecting and discussing existing information, and a context Miro board has been created that is being used to crowdsource relevant information about power and carbon data sources and how they are created and used from end to end. The Miro is publicly readable here.
Governance
This project is governed by the ‣