Carbon-Aware Computing for Datacenters

By A. Radovanovic, R. Koningstein, Ian Schneider, Bokan Chen, A. Duarte, Binz Roy, Diyue Xiao, Maya Haridasan, P. Hung, Nick Care and 5 more. 2021

296 citations recorded by the source corpus.

The amount of CO$_{2}$ emitted per kilowatt-hour on an electricity grid varies by time of day and substantially varies by location due to the types of generation. Networked collections of warehouse scale computers, sometimes called Hyperscale Computing, emit more carbon than needed if operated without regard to these variations in carbon intensity. This paper introduces Google’s system for global Carbon-Intelligent Compute Management, which actively minimizes electricity-based carbon footprint and power infrastructure costs by delaying temporally flexible workloads. The core component of the system is a suite of analytical pipelines used to gather the next day’s carbon intensity forecasts, train day-ahead demand prediction models, and use risk-aware optimization to generate the next day’s carbon-aware Virtual Capacity Curves (VCCs) for all datacenter clusters across Google’s fleet. VCCs impose hourly limits on resources available to temporally flexible workloads while preserving overall daily capacity, enabling all such workloads to complete within a day with high probability. Data from Google’s in-production operation shows that VCCs effectively limit hourly capacity when the grid’s energy supply mix is carbon intensive and delay the execution of temporally flexible workloads to “greener” times.

Subfields: Computer Networks and Communications, Information Systems, Information Systems and Management, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Evaluation & Benchmarks

Citations in the corpus

Sustainable AI: Environmental Implications, Challenges and Opportunities (2021, background): “Elastic carbon-aware workload scheduling techniques can be used in and across datacenters to predict and exploit the intermittent energy generation patterns (Radovanovic et al., 2021).”
ACT: designing sustainable computer systems with an architectural carbon modeling tool (2022, background): “Recent efforts at the cloud-scale enable renewable energy-driven warehouse-scale data centers [6, 16, 24, 66, 97].”
Socio-Technological Challenges and Opportunities: Paths Forward (2021, background): “…for a resilient and consistent power grid, IT infrastructure may be better served by (co-)designing agile applications and data centers, such as [Íñigo Goiri et al., 2015, Radovanovic et al., 2021, Lin et al., 2021, Zhang et al., 2021], that implicitly assume power fluctuations and variability.”
A Holistic Approach for Designing Carbon Aware Datacenters (2022, background): “Optimization objectives have accounted for electricity prices [44], carbon prices in cap-and-trade markets [31], the carbon-intensity of grid energy [50], and service quality [28].”