CoChat
Sign Up
Cited by 353Cloud Computing and Resource ManagementEnergy Efficiency in ComputingSmart Grid Energy Management

Carbon-aware computing for datacenters

Open access
Radovanović, Ana, Koningstein, Ross, Schneider, Ian, Chen, Bokan, Duarte, Alexandre, Roy, Binz, Xiao, Diyue, Haridasan, Maya +7 more·2023·IEEE Transactions on Power Systems
DOI 10.1109/tpwrs.2022.3173250
Open this paper in CoChat — free accountOpen PDF

Abstract

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpwrs.2022.3173250

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The carbon-aware scheduling of Radovanović et al. (2023) shifts temporally flexible data-center load toward low-carbon hours, which is an appropriation rule in Ostrom's sense.

    “The carbon-aware scheduling of Radovanović et al. (2023) shifts temporally flexible data-center load toward low-carbon hours, which is an appropriation rule in Ostrom's sense, congruence between the timing of withdrawal and the condition of the shared grid, implemented in software.”

    From Commons-Governed Artificial Intelligence: A Taxonomy of Collective Governance (2026) · cites this paper as Radovanović et al. (2023)

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 54 · Cited by 353

Research works printed but not linked: 29

  1. M. Dayarathna, Y. Wen, and R. Fan, "Data center energy consump- tion modeling: A survey," IEEE Commun. Surv. Tut., vol. 18, no. 1, pp. 732-794, Jan.-Mar. 2016.
  2. M. Li, T. M. Smith, Y. Yang, and E. J. Wilson, "Marginal emission factors considering renewables: A case study of the US midcontinent independent system operator (MISO) system," Environ. Sci. Technol., vol. 51, no. 19, pp. 11215-11223, 2017.
  3. M. P. Thind, E. J. Wilson, I. L. Azevedo, and J. D. Marshall, "Marginal emissions factors for electricity generation in the midcontinent ISO," Environ. Sci. Technol., vol. 51, no. 24, pp. 14445-14452, 2017.
  4. D. S. Callaway, M. Fowlie, and G. McCormick, "Location, location, loca- tion: The variable value of renewable energy and demand-side efficiency resources," J. Assoc. Environ. Resour. Economists, vol. 5, no. 1, pp. 39-75, 2018.
  5. I. Khan, "Temporal carbon intensity analysis: Renewable versus fossil fuel dominated electricity systems," Energy Sources, Part A: Recovery, Utilization, Environ. Effects, vol. 41, no. 3, pp. 309-323, 2019.
  6. D. Rolnick et al., "Tackling climate change with machine learning," ACM Comput. Surv. (CSUR), vol. 55, no. 2, pp. 1-96, Feb. 8, 2022.
  7. J. Guitart, "Toward sustainable data centers: A comprehensive energy management strategy," Computing, vol. 99, pp. 597-615, 2017.
  8. A. H. Mahmud and S. S. Iyengar, "A distributed framework for carbon and cost aware geographical job scheduling in a hybrid data center in- frastructure," in Proc. IEEE Int. Conf. Autonomic Comput. (ICAC), 2016, pp. 75-84.
  9. M. A. Islam, S. Ren, and X. Wang, "Greencolo: A novel incentive mech- anism for minimizing carbon footprint in colocation data center," in Proc. Int. Green Comput. Conf., 2014, pp. 1-8.
  10. K. Le, R. Bianchini, T. D. Nguyen, O. Bilgir, and M. Martonosi, "Capping the brown energy consumption of internet services at low cost," in Proc. Int. Conf. Green Comput., 2010, pp. 3-14.
  11. X. Deng, D. Wu, J. Shen, and J. He, "Eco-aware online power management and load scheduling for green cloud datacenters," IEEE Syst. J., vol. 10, no. 1, pp. 78-87, Mar. 2016.
  12. J. Berral, Í. Goiri, T. Nguyen, R. Gavalda, J. Torres, and R. Bianchini, "Building green cloud services at low cost," in Proc. IEEE 34th Int. Conf. Distrib. Comput. Syst., 2014, pp. 449-460.
  13. Z. Liu, M. Lin, A. Wierman, S. H. Low, and L. L. Andrew, "Geographical load balancing with renewables," in ACM SIGMETRICS Perform. Eval. Rev., vol. 39, pp. 62-66, 2011.
  14. Z. Liu, M. Lin, A. Wierman, S. Low, and L. Andrew, "Greening geograph- ical load balancing," IEEE/ACM Trans. Netw., vol. 23, no. 2, pp. 657-671, Apr. 2015.
  15. J. Zheng, A. Chien, and S. Suh, "Mitigating curtailment and carbon emissions through load migration between data centers," Joule, vol. 4, no. 10, pp. 2208-2222, 2020.
  16. A. Rahman, X. Liu, and F. Kong, "A survey on geographic load balancing based data center power management in the smart grid environment," IEEE Commun. Surv. Tut., vol. 16, no. 1, pp. 214-233, Jan.-Mar. 2014.
  17. C. Kelly, J. Ging, A. Kansal, and M. Walsh, "Balancing power systems with datacenters using a virtual interconnector," IEEE Power Energy Technol. Syst. J., vol. 3, no. 2, pp. 51-59, Jun. 2016.
  18. A. James and D. Schien, "A law karbon kubernetes scheduler," in Proc. ICT4S, Jan. 2019. [Online]. Available: http://ceur-ws.org/Vol-2382/ ICT4S2019_paper_28.pdf
  19. C. Ren, D. Wang, B. Urgaonkar, and A. Sivasubramaniam, "Carbon-aware energy capacity planning for datacenters," in Proc. IEEE 20th Int. Symp. Model., Anal. Simul. Comput. Telecommun. Syst., 2012, pp. 391-400.
  20. Z. Liu et al., "Renewable and cooling aware workload management for sustainable data centers," in ACM SIGMETRICS Perform. Eval. Rev., vol. 40, pp. 175-186, 2012.
  21. Í. Goiri et al., "Greenslot: Scheduling energy consumption in green data- centers," in Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal., 2011, pp. 1-11.
  22. Í. Goiri et al., "GreenHadoop: Leveraging green energy in data-processing frameworks," in Proc. 7th ACM Eur. Conf. Comput. Syst., 2012, pp. 57-70.
  23. M. Tirmazi et al., "Borg: The next generation," in Proc. EuroSys' 20, Heraklion, Crete, 2020, pp. 1-14.
  24. A. Radovanović, B. Chen, S. Talukdar, B. Roy, A. Duarte, and M. Shahbazi, "Power modeling for effective datacenter planning and compute management," IEEE Trans. Smart Grid, vol. 13, no. 2, pp. 1611-1621, Mar. 2022.
  25. B. Beyer, C. Jones, J. Petoff, and N. R. Murphy, Site Reliability Engi- neering: How Google Runs Production Systems. Sebastopol, CA, USA: O'Reilly Media, Inc., 2016.
  26. L. A. Barroso, U. Hölzle, and P. Ranganathan, "The datacenter as a com- puter: Designing warehouse-scale machines," Synth. Lectures Comput. Architecture, vol. 13, no. 3, pp. 1-189, 2018.
  27. J. Dean and S. Ghemawat, "Mapreduce: Simplified data processing on large clusters," in Proc. 6th Symp. Operating Syst. Des. Implementation, 2004, pp. 137-150.
  28. X. Fan, W.-D. Weber, and L. A. Barroso, "Power provisioning for a warehouse-sized computer," ACM SIGARCH Comput. Architecture News, vol. 35, no. 2, pp. 13-23, 2007.
  29. S. Rivoire, P. Ranganathan, and C. Kozyrakis, "A comparison of high-level full-system power models," HotPower, vol. 8, no. 2, pp. 32-39, 2008.

Authors
Radovanović, A., Koningstein, R., Schneider, I., Chen, B., Duarte, A., Roy, B., Xiao, D., Haridasan, M., Hung, P., Care, N., Talukdar, S., Mullen, E., Smith, K., Cottman, M., & Cirne, W.
Affiliations
Google (United States) (US)
ORCID
Venue
IEEE Transactions on Power Systems
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2023-03
Volume
38
Issue
2
Pages
1270-1280
ISSN
  • 0885-8950 (ISSN-L)
  • 1558-0679
DOI
10.1109/tpwrs.2022.3173250
OpenAlex
W3175111539
Cited by
353
References
54
Citations by year
2026: 160 · 2025: 70 · 2024: 72 · 2023: 32 · 2022: 14 · 2021: 5
FWCI
46.52
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Power Systems (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
Google
Topics
  • Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
  • Physical Sciences › Computer Science › Hardware and Architecture › Energy Efficiency in Computing
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Smart Grid Energy Management
Keywords
carbon-aware computing, data centers, carbon intensity forecasting, demand forecasting, workload scheduling, carbon footprint, energy mix, risk-aware optimization, Google

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review