Stochastic switching model and policy optimization online for dynamic power management

被引:2
|
作者
Jiang, Qi [1 ]
Xi, Hong-Sheng [1 ]
Yin, Bao-Qun [1 ]
机构
[1] Department of Automation, University of Science and Technology of China, Hefei 230027, China
来源
关键词
Computer simulation - Markov processes - Optimization - Reinforcement learning;
D O I
10.1360/aas-007-0066
中图分类号
学科分类号
摘要
A reinforcement learning based online optimization algorithm is presented for dynamic power management with unknown system parameters. First an event-driven stochastic switching model is introduced to formulate dynamic power management problem as a constrained policy optimization problem. Then by utilizing the features of this model an online optimization algorithm that combines policy gradient estimation and stochastic approximation is derived. The stochastic switching model captures the power-managed system behaves accurately. The optimization algorithm is adaptive, and can achieve global optimum with less computational cost. Simulation results demonstrate the effectiveness of the proposed approach.
引用
收藏
页码:66 / 71
相关论文
共 50 条
  • [21] Stochastic Optimization of Wind Turbine Power Factor Using Stochastic Model of Wind Power
    Chen, Peiyuan
    Siano, Pierluigi
    Bak-Jensen, Birgitte
    Chen, Zhe
    IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, 2010, 1 (01) : 19 - 29
  • [22] Online Learning of Timeout Policies for Dynamic Power Management
    Khan, Umair Ali
    Rinner, Bernhard
    ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2014, 13 (04)
  • [23] A Gradient Learning Optimization for Dynamic Power Management
    Li, Yanjie
    Jiang, Frank
    2015 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2015): BIG DATA ANALYTICS FOR HUMAN-CENTRIC SYSTEMS, 2015, : 2061 - 2066
  • [24] Online optimization with switching cost
    1600, Association for Computing Machinery, 2 Penn Plaza, Suite 701, New York, NY 10121-0701, United States (40):
  • [25] COMPOUND DYNAMIC CONSTRAINT OF STOCHASTIC OPTIMIZATION MODEL AND ALGORITHM
    Zhou, Lei
    Li, Fa-Chao
    PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION, VOLS 1 AND 2, 2008, : 783 - 787
  • [26] The effects of the near-zero interest rate policy in a regime-switching dynamic stochastic general equilibrium model
    Chen, Han
    JOURNAL OF MONETARY ECONOMICS, 2017, 90 : 176 - 192
  • [27] Hybrid Model for Dynamic Power Management
    Lee, Wai-Kong
    Lee, Sze-Wei
    Siew, Wee-Ong
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2009, 55 (02) : 656 - 664
  • [28] An optimization model for stochastic wind power capacity allocation
    Li, Shuting
    Liu, Yan
    Han, Xingning
    Li, Jiaming
    Wen, Jinyu
    Yi, Haiqiong
    Song, Zhuoran
    Dianwang Jishu/Power System Technology, 2015, 39 (06): : 1697 - 1702
  • [29] An efficient dynamic power management policy on sensor network
    Luo, RC
    Tu, LC
    Chen, O
    AINA 2005: 19TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS, VOL 2, 2005, : 341 - 344
  • [30] Online Stochastic and robust optimization
    Bent, R
    Van Hentenryck, P
    ADVANCES IN COMPUTER SCIENCE - ASIAN 2004, PROCEEDINGS, 2004, 3321 : 286 - 300