Reinforcement learning-based dynamic power management of a battery-powered system supplying multiple active modes

Maryam Triki, Ahmed C. Ammari, Yanzhi Wang, Massoud Pedram

Research output: Contribution to conferencePaper

6 Scopus citations

Abstract

This paper addresses the problem of extending battery service lifetime in a portable electronic system while maintaining an acceptable performance degradation level. The proposed dynamic power management (DPM) framework is based on model-free reinforcement learning (RL) technique. In this DPM framework, the Power Manager (PM) adapts the system operating mode to the actual battery state of charge. It uses RL technique to accurately define the optimal battery voltage threshold value and use it to specify the system active mode. In addition, the PM automatically adjusts the power management policy by learning the optimal timeout value. Moreover, the SoC and latency tradeoffs can be precisely controlled based on a user-defined parameter. Experiments show that the proposed method outperforms existing methods by 35% in terms of saving battery service lifetime.

Original languageEnglish (US)
Pages437-442
Number of pages6
DOIs
StatePublished - Jan 1 2013
EventUKSim-AMSS 7th European Modelling Symposium on Computer Modelling and Simulation, EMS 2013 - Manchester, United Kingdom
Duration: Nov 20 2013Nov 22 2013

Other

OtherUKSim-AMSS 7th European Modelling Symposium on Computer Modelling and Simulation, EMS 2013
CountryUnited Kingdom
CityManchester
Period11/20/1311/22/13

Keywords

  • battery-powered system design
  • Dynamic power management
  • extending battery lifetime
  • reinforcement learning

ASJC Scopus subject areas

  • Modeling and Simulation

Fingerprint Dive into the research topics of 'Reinforcement learning-based dynamic power management of a battery-powered system supplying multiple active modes'. Together they form a unique fingerprint.

  • Cite this

    Triki, M., Ammari, A. C., Wang, Y., & Pedram, M. (2013). Reinforcement learning-based dynamic power management of a battery-powered system supplying multiple active modes. 437-442. Paper presented at UKSim-AMSS 7th European Modelling Symposium on Computer Modelling and Simulation, EMS 2013, Manchester, United Kingdom. https://doi.org/10.1109/EMS.2013.74