Power management optimisation for hybrid electric systems using reinforcement learning and adaptive dynamic programming

被引：5
|
作者：
Sanusi, Ibrahim [1 ]
Mills, Andrew [1 ]
Konstantopoulos, George [1 ]
Dodd, Tony [1 ]
机构：
[1] Univ Sheffield, Dept Automat Control & Syst Engn, Sheffield, S Yorkshire, England
来源：
2019 AMERICAN CONTROL CONFERENCE (ACC) | 2019年
关键词：
DESIGN;
D O I：
10.23919/acc.2019.8814407
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents an online learning scheme based on reinforcement learning and adaptive dynamic programming for the power management of hybrid electric systems. Current methods for power management are conservative and unable to fully account for variations in the system due to changes in the health and operational conditions. These conservative schemes result in less efficient use of available power sources, increasing the overall system costs and heightening the risk of failure due to the variations. The proposed scheme is able to compensate for modelling uncertainties and the gradual system variations by adapting its performance function using the observed system measurements as reinforcement signals. The reinforcement signals are nonlinear and consequently neural networks are employed in the implementation of the scheme. Simulation results for the power management of an autonomous hybrid system show improved system performance using the proposed scheme as compared with a conventional offline dynamic programming approach.
引用
收藏
页码：2608 / 2613
页数：6
相关论文
共 50 条
  • [1] Optimization of power management in an hybrid electric vehicle using dynamic programming
    Perez, Laura V.
    Bossio, Guillermo R.
    Moitre, Diego
    Garcia, Guillermo O.
    [J]. MATHEMATICS AND COMPUTERS IN SIMULATION, 2006, 73 (1-4) : 244 - 254
  • [2] A Reinforcement Learning Based Dynamic Power Management for Fuel Cell Hybrid Electric Vehicle
    Hsu, Roy Chaoming
    Chen, Shi-Mao
    Chen, Wen-Yen
    Liu, Cheng-Ting
    [J]. 2016 JOINT 8TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS (SCIS) AND 17TH INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS (ISIS), 2016, : 460 - 464
  • [3] Power management in hybrid electric vehicles using deep recurrent reinforcement learning
    Sun, Mengshu
    Zhao, Pu
    Lin, Xue
    [J]. ELECTRICAL ENGINEERING, 2022, 104 (03) : 1459 - 1471
  • [4] Power management in hybrid electric vehicles using deep recurrent reinforcement learning
    Mengshu Sun
    Pu Zhao
    Xue Lin
    [J]. Electrical Engineering, 2022, 104 : 1459 - 1471
  • [5] Reinforcement Learning Based Power Management for Hybrid Electric Vehicles
    Lin, Xue
    Wang, Yanzhi
    Bogdan, Paul
    Chang, Naehyuck
    Pedram, Massoud
    [J]. 2014 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD), 2014, : 32 - 38
  • [6] Dynamic Energy Management for Hybrid Electric Vehicle Based on Adaptive Dynamic Programming
    Li, Weimin
    Xu, Guoqing
    Wang, Zhancheng
    Xu, Yangsheng
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY, VOLS 1-5, 2008, : 699 - +
  • [7] Reinforcement Learning Based Dynamic Power Management with a Hybrid Power Supply
    Yue, Siyu
    Zhu, Di
    Wang, Yanzhi
    Pedram, Massoud
    [J]. 2012 IEEE 30TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD), 2012, : 81 - 86
  • [8] Computationally Efficient Energy Management for a Parallel Hybrid Electric Vehicle Using Adaptive Dynamic Programming
    Liu, Tong
    Tan, Kaige
    Zhu, Wenyao
    Feng, Lei
    [J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2024, 9 (02): : 4085 - 4099
  • [9] Power Management for Plug-in Hybrid Electric Vehicles using Reinforcement Learning with Trip Information
    Liu, Chang
    Murphey, Yi Lu
    [J]. 2014 IEEE TRANSPORTATION ELECTRIFICATION CONFERENCE AND EXPO (ITEC), 2014,
  • [10] An Energy Management Strategy of Power-Split Hybrid Electric Vehicles Using Reinforcement Learning
    Zhou, Juanying
    Zhao, Jianyou
    Wang, Lufeng
    [J]. MOBILE INFORMATION SYSTEMS, 2022, 2022
12345