ACE: Abstracting, characterizing and exploiting datacenter power demands

Di Wang, Chuangang Ren, Sriram Govindan, Anand Sivasubramaniam, Bhuvan Urgaonkar, Aman Kansal, Kushagra Vaid

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

15 Scopus citations

Abstract

Peak power management of datacenters has tremendous cost implications. While numerous mechanisms have been proposed to cap power consumption, real datacenter power consumption data is scarce. Prior studies have either used a small set of applications and/or servers, or presented data that is at an aggregate scale from which it is difficult to design and evaluate new and existing optimizations. To address this gap, we collect power measurement data at multiple spatial and fine-grained temporal resolutions from several geo-distributed datacenters of Microsoft corporation over 6 months. We conduct aggregate analysis of this data to study its statistical properties. We find evidence of self-similarity in power demands, statistical multiplexing effects, and correlations with the cooling power that caters to the IT equipment. With workload characterization a key ingredient for systems design and evaluation, we note the importance of better abstractions for capturing power demands, in the form of peaks and valleys. We identify attributes for peaks and valleys, and important correlations across these attributes that can influence the choice and effectiveness of different power capping techniques. We characterize these attributes and their correlations, showing the burstiness of small duration peaks, and the importance of not ignoring the rare but more stringent or long peaks. The correlations between peaks and valleys suggest the need for techniques to aggregate and collectively handle them. With the wide scope of exploitability of such characteristics for power provisioning and optimizations, we illustrate its benefits with two specific case studies. The first shows how peaks can be differentially handled based on our peak and valley characterization using existing approaches, rather than a one-size-fits-all solution. The second illustrates a simple capacity provisioning strategy for energy storage using the peak and valley characteristics.

Original languageEnglish (US)
Title of host publicationProceedings - 2013 IEEE International Symposium on Workload Characterization, IISWC 2013
PublisherIEEE Computer Society
Pages44-55
Number of pages12
ISBN (Print)9781479905539
DOIs
StatePublished - Jan 1 2013
Event2013 IEEE International Symposium on Workload Characterization, IISWC 2013 - Portland, OR, United States
Duration: Sep 22 2013Sep 24 2013

Publication series

NameProceedings - 2013 IEEE International Symposium on Workload Characterization, IISWC 2013

Other

Other2013 IEEE International Symposium on Workload Characterization, IISWC 2013
CountryUnited States
CityPortland, OR
Period9/22/139/24/13

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'ACE: Abstracting, characterizing and exploiting datacenter power demands'. Together they form a unique fingerprint.

  • Cite this

    Wang, D., Ren, C., Govindan, S., Sivasubramaniam, A., Urgaonkar, B., Kansal, A., & Vaid, K. (2013). ACE: Abstracting, characterizing and exploiting datacenter power demands. In Proceedings - 2013 IEEE International Symposium on Workload Characterization, IISWC 2013 (pp. 44-55). [6704669] (Proceedings - 2013 IEEE International Symposium on Workload Characterization, IISWC 2013). IEEE Computer Society. https://doi.org/10.1109/IISWC.2013.6704669