• 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于强化学习的综合能源系统管理综述

熊珞琳,  毛帅,  唐漾,  孟科,  董朝阳,  钱锋

文章导航 > 自动化学报  > 2021 >  47(10): 2321-2340
熊珞琳, 毛帅, 唐漾, 孟科, 董朝阳, 钱锋. 基于强化学习的综合能源系统管理综述. 自动化学报, 2021, 47(10): 2321−2340 doi: 10.16383/j.aas.c210166
引用本文: 熊珞琳, 毛帅, 唐漾, 孟科, 董朝阳, 钱锋. 基于强化学习的综合能源系统管理综述. 自动化学报, 2021, 47(10): 2321−2340 doi: 10.16383/j.aas.c210166
shu
Xiong Luo-Lin, Mao Shuai, Tang Yang, Meng Ke, Dong Zhao-Yang, Qian Feng. Reinforcement learning based integrated energy system management: A survey. Acta Automatica Sinica, 2021, 47(10): 2321−2340 doi: 10.16383/j.aas.c210166
Citation: Xiong Luo-Lin, Mao Shuai, Tang Yang, Meng Ke, Dong Zhao-Yang, Qian Feng. Reinforcement learning based integrated energy system management: A survey. Acta Automatica Sinica, 2021, 47(10): 2321−2340 doi: 10.16383/j.aas.c210166
shu

基于强化学习的综合能源系统管理综述

doi: 10.16383/j.aas.c210166
  • 1.

    华东理工大学信息科学与工程学院 上海 200237 中国

  • 2.

    新南威尔士大学电气工程与电子通信学院 新南威尔士州 2052 澳大利亚

基金项目: 国家自然科学基金基础科学中心项目(61988101), 国家杰出青年科学基金(61725301), 中央高校基本科研业务费专项资金(222202117006), 上海市优秀学术带头人计划(20XD1401300)资助
详细信息
    作者简介:

    熊珞琳：华东理工大学信息科学与工程学院博士研究生. 主要研究方向为强化学习, 智能电网. E-mail: Y11200038@mail.ecust.edu.cn

    毛帅：华东理工大学信息科学与工程学院博士研究生. 主要研究方向为多智能体系统, 分布式优化. E-mail: mshecust@163.com

    唐漾：博士, 华东理工大学教授. 主要研究方向为分布式估计/控制/优化, 信息物理融合系统, 混杂动力系统, 计算机视觉和强化学习. E-mail: yangtang@ecust.edu.cn

    孟科：博士, 澳大利亚新南威尔士大学电气工程与电信学院高级讲师. 主要研究方向为电力系统建模, 稳定性分析, 可再生能源系统和电网集成. E-mail: kemeng@ieee.org

    董朝阳：博士, 澳大利亚新南威尔士大学电气工程与电信学院能源系统教授. 主要研究方向为智能电网, 电力系统规划, 电力系统安全, 负荷建模, 电力市场和计算智能及其在电力工程中的应用. E-mail: zydong@ieee.org

    钱锋：博士, 中国工程院院士, 华东理工大学副校长. 主要研究方向为化工过程资源与能源高效利用的流程制造智能控制, 系统集成优化理论方法与关键技术研究. 本文通信作者. E-mail: fqian@ecust.edu.cn

Reinforcement Learning Based Integrated Energy System Management: A Survey

  • 1.

    School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China

  • 2.

    School of Electrical Engineering and Telecommunications, University of New South Wales, NSW 2052, Australia

Funds: Supported by Project of Basic Science Center of National Natural Science Foundation of China (61988101), National Science Fund for Distinguished Young Scholars (61725301), the Fundamental Research Funds for the Central Universities (222202117006), and Program of Shanghai Academic Research Leader (20XD1401300)
More Information
    Author Bio:

    XIONG Luo-Lin　Ph. D. candidate at School of Information Science and Engineering, East China University of Science and Technology. Her research interest covers reinforcement learning, and smart grid

    MAO Shuai　Ph. D. candidate at School of Information Science and Engineering, East China University of Science and Technology. His research interest covers multi-agent systems, and distributed optimization

    TANG Yang　Ph. D., professor at East China University of Science and Technology. His research interest covers distributed estimation/control/optimization, cyber-physical systems, hybrid dynamical systems, computer vision, and reinforcement learning

    MENG Ke　Ph. D., senior lecturer at the School of Electrical Engineering and Telecommunications, University of New South Wales, Australia. His research interest covers electric power system modelling, stability analysis, renewable energy systems, and grid integration

    DONG Zhao-Yang　Ph. D., professor of energy systems at the School of Electrical Engineering and Telecommunications, University of New South Wales, Australia. His research interest covers smart grid, electric power system planning, electric power system security, load modeling, electricity market, and computational intelligence and its application in power engineering

    QIAN Feng　Ph. D., Academician of Chinese Academy of Engineering, the Vice President of East China University of Science and Technology. His research interest covers intelligent control of process manufacturing for efficient utilization of chemical process resources and energy, and theory, method and key technology of system integrated optimization. Corresponding author of this paper

    摘要
  • 摘要: 为了满足日益增长的能源需求并减少对环境的破坏, 节能成为全球经济和社会发展的一项长远战略方针, 加强能源管理能够提高能源利用效率、促进节能减排. 然而, 可再生能源和柔性负载的接入使得综合能源系统(Integrated energy system, IES)发展成为具有高度不确定性的复杂动态系统, 给现代化能源管理带来巨大的挑战. 强化学习(Reinforcement learning, RL)作为一种典型的交互试错型学习方法, 适用于求解具有不确定性的复杂动态系统优化问题, 因此在综合能源系统管理问题中得到广泛关注. 本文从模型和算法的层面系统地回顾了利用强化学习求解综合能源系统管理问题的现有研究成果, 并从多时间尺度特性、可解释性、迁移性和信息安全性4个方面提出展望.
    Abstract: In order to meet the growing energy demand and reduce the damage to the environment, energy conservation has become a long-term strategic policy for global economic and social development. The enhancement of energy management can improve energy efficiency, as well as promote energy conservation and emission reduction. However, the integration of renewable energy and flexible load makes the integrated energy system (IES) become a complex dynamic system with high uncertainty, which brings great challenges to modern energy management. Reinforcement learning (RL), as a typical interactive trial-and-error learning method, is suitable for solving optimization problems of complex dynamic systems with uncertainty, and therefore it has been widely considered in integrated energy system management. This paper systematically reviews the existing works of using reinforcement learning to solve integrated energy system management problems from the perspective of models and algorithms, and puts forward prospects from four aspects: Multi-time scale, interpretability, transferability, and information security.
    • HTML全文