Stochastic Control of Power Supply in Data Centers

Georgios Rovatsos, Shaofeng Zou, Alejandro D. Dominguez-Garcia, Venugopal V. Veeravalli

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

Abstract

The problem of operating the power supply system of a data center in a reliable manner is studied. Two approaches are examined. The first one assumes that there is no control over the power supply system. The second one assumes that there is a control over the maximum capacity of the system load. For the second case, the problem is fitted into a dynamic programming (DP) framework. An optimal control policy is derived, however is intractable. An approximate solution is then constructed by the Perseus algorithm. This solution is compared to two easily implementable heuristic algorithms, and with the case where no system control is allowed. Numerical results show that the approximate solution has a superior performance.

Original languageEnglish (US)
Title of host publicationConference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages1470-1474
Number of pages5
ISBN (Electronic)9781538692189
DOIs
StatePublished - Jul 2 2018
Event52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 - Pacific Grove, United States
Duration: Oct 28 2018Oct 31 2018

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2018-October
ISSN (Print)1058-6393

Conference

Conference52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
Country/TerritoryUnited States
CityPacific Grove
Period10/28/1810/31/18

Keywords

  • Smart grid
  • dynamic load control
  • power distribution networks

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Stochastic Control of Power Supply in Data Centers'. Together they form a unique fingerprint.

Cite this