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
  • [41] A stochastic dynamic programming model for the management of the saiga antelope
    MilnerGulland, EJ
    ECOLOGICAL APPLICATIONS, 1997, 7 (01) : 130 - 142
  • [42] Power Management System for Online Low Power RF Energy Harvesting Optimization
    Dolgov, Arseny
    Zane, Regan
    Popovic, Zoya
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2010, 57 (07) : 1802 - 1811
  • [43] Multi-Stage Resilience Management of Smart Power Distribution Systems: A Stochastic Robust Optimization Model
    Dehghani, Nariman L.
    Shafieezadeh, Abdollah
    IEEE TRANSACTIONS ON SMART GRID, 2022, 13 (05) : 3452 - 3467
  • [44] Stochastic Dynamic Programming Model for Revenue Optimization in Social Networks
    Hosein, Patrick
    Lawrence, Trisha
    2015 IEEE 11TH INTERNATIONAL CONFERENCE ON WIRELESS AND MOBILE COMPUTING, NETWORKING AND COMMUNICATIONS (WIMOB), 2015, : 378 - 383
  • [45] Applying Dynamic Power Management with Mode Switching in Wireless Sensor Networks
    Sausen, P. S.
    Spohn, M. A.
    Salvadori, F.
    de Campos, M.
    Perkusich, A.
    IECON 2008: 34TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-5, PROCEEDINGS, 2008, : 1651 - +
  • [46] Dynamic Power Management with Scheduled Switching Modes in Wireless Sensor Networks
    Sausen, P. S.
    Sousa, J. R. B.
    Spohn, M. A.
    Perkusich, A.
    Lima, A. M. N.
    PROCEEDINGS OF MASCOTS '07: 15TH INTERNATIONAL SYMPOSIUM ON MODELING, ANALYSIS, AND SIMULATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS, 2007, : 1 - +
  • [47] Stochastic Robust Mathematical Programming Model for Power System Optimization
    Liu, Cong
    Lee, Changhyeok
    Chen, Haoyong
    Mehrotra, Sanjay
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2016, 31 (01) : 821 - 822
  • [48] System Message Based Predict Policy for Dynamic Power Management
    Ma, Xi-Qiang
    Yang, Fang
    Li, Ji-Shun
    Xue, Yu-Jun
    PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATION AND SENSOR NETWORKS (WCSN 2016), 2016, 44 : 580 - 584
  • [49] Online Advertisement, Optimization and Stochastic Networks
    Tan, Bo
    Srikant, R.
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2012, 57 (11) : 2854 - 2868
  • [50] ONLINE OPTIMIZATION OF STOCHASTIC-PROCESSES
    MORSHEDI, AM
    LUECKE, RH
    INDUSTRIAL & ENGINEERING CHEMISTRY PROCESS DESIGN AND DEVELOPMENT, 1977, 16 (04): : 473 - 478