Online server and workload management for joint optimization of electricity cost and carbon footprint across data centers

Zahra Abbasi, Madhurima Pore, Sandeep Gupta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

Internet data centers, typically distributed across the world in order to provide timely and reliable Internet service, have been increasingly pressurized to reduce their carbon footprint and electricity cost. Particularly, data centers will soon be required to abide by carbon capping polices which impose carbon footprint limits to encourage brown energy conservation. We propose an online algorithm, called OnlineCC, for minimizing the operational cost while satisfying the carbon footprint reduction target of a set of geo-distributed data centers. OnlineCC makes use of Lyapunov optimization technique while operating without long-term future information, making it attractive in the presence of uncertainties associated with data center information e.g., input workload. We prove that OnlineCC achieves a near optimal operational cost (electricity cost) compared to the optimal algorithm with future information, while bounding the potential violation of carbon footprint target, depending on the Lyapunov control parameter, namely V. We also give a heuristic for finding V which significantly shortens the search space to adjust its value. Finally, we perform a trace-based simulation study and a small scale experiment to complement the analysis. The results show that OnlineCC reduces cost by more than 18% compared to a prediction-based online solution while resulting in equal or smaller carbon footprint.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS 2014
PublisherIEEE Computer Society
Pages317-326
Number of pages10
ISBN (Print)9780769552071
DOIs
StatePublished - Jan 1 2014
Event28th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2014 - Phoenix, AZ, United States
Duration: May 19 2014May 23 2014

Publication series

NameProceedings of the International Parallel and Distributed Processing Symposium, IPDPS
ISSN (Print)1530-2075
ISSN (Electronic)2332-1237

Other

Other28th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2014
CountryUnited States
CityPhoenix, AZ
Period5/19/145/23/14

Keywords

  • carbon capping
  • carbon neutrality
  • cloud computing
  • cost saving
  • data centers
  • energy sustainability

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Fingerprint Dive into the research topics of 'Online server and workload management for joint optimization of electricity cost and carbon footprint across data centers'. Together they form a unique fingerprint.

  • Cite this

    Abbasi, Z., Pore, M., & Gupta, S. (2014). Online server and workload management for joint optimization of electricity cost and carbon footprint across data centers. In Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS 2014 (pp. 317-326). [6877266] (Proceedings of the International Parallel and Distributed Processing Symposium, IPDPS). IEEE Computer Society. https://doi.org/10.1109/IPDPS.2014.42