Enhanced Q-learning algorithm for dynamic power management with performance constraint

Wei Liu, Ying Tan, Qinru Qiu

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

26 Scopus citations

Abstract

This paper presents a novel power management techniques based on enhanced Q-learning algorithms. By exploiting the submodularity and monotonic structure in the cost function of a power management system, the enhanced Q-learning algorithm is capable of exploring ideal trade-offs in the power-performance design space and converging to a better power management policy. We further propose a linear adaption algorithm that adapts the Lagrangian multiplier λ to search for the power management policy that minimizes the power consumption while delivering the exact required performance. Experimental results show that, comparing to the existing expert-based power management, the proposed Q-learning based power management achieves up to 30% and 60% reduction in power saving for synthetic workload and real workload, respectively while in average maintain a performance within 7% variation of the given constraint.

Original languageEnglish (US)
Title of host publicationDATE 10 - Design, Automation and Test in Europe
Pages602-605
Number of pages4
StatePublished - Jun 9 2010
Externally publishedYes
EventDesign, Automation and Test in Europe Conference and Exhibition, DATE 2010 - Dresden, Germany
Duration: Mar 8 2010Mar 12 2010

Publication series

NameProceedings -Design, Automation and Test in Europe, DATE
ISSN (Print)1530-1591

Other

OtherDesign, Automation and Test in Europe Conference and Exhibition, DATE 2010
CountryGermany
CityDresden
Period3/8/103/12/10

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Enhanced Q-learning algorithm for dynamic power management with performance constraint'. Together they form a unique fingerprint.

  • Cite this

    Liu, W., Tan, Y., & Qiu, Q. (2010). Enhanced Q-learning algorithm for dynamic power management with performance constraint. In DATE 10 - Design, Automation and Test in Europe (pp. 602-605). [5457135] (Proceedings -Design, Automation and Test in Europe, DATE).