基于Q学习的区域综合能源系统低碳运行策略研究
DOI:
作者:
作者单位:

1.国网福建省电力有限公司经济技术研究院;2.武汉大学电气与自动化学院

作者简介:

通讯作者:

中图分类号:

TM73; TK018

基金项目:

国家自然科学基金项目;国网福建省电力有限公司经济技术研究院科技项目


Low-carbon Operation Strategy of Regional Integrated Energy System Based on Q Learning Algorithm
Author:
Affiliation:

1.Economic Technology Research Institute,State Grid Fujian Electric Power Co,Ltd;2.School of Electrical Engineering and Automation,Wuhan University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    在全球能源短缺、环境污染的背景下,在电力系统中引入区域综合能源系统(regional integrated energy system, RIES)是提高清洁能源在终端占比、提高能源利用率的重要手段。为了实现RIES的低碳经济运行,首先搭建了RIES的基本结构模型,接着充分考虑二氧化碳排放量的治理费用,以RIES日运行费用最低为目标函数构建了RIES运行策略的数学模型,然后建立该模型的马尔可夫决策过程(Markov decision process, MDP)问题,并引入改进的Q学习(Q learning)算法以寻求RIES的最佳运行策略。仿真结果表明:所提模型能实现RIES的多能互补,能在满足供需平衡的基础上实现RIES的低碳经济运行,继而最终实现能源的高效灵活运用。

    Abstract:

    In the context of global energy shortage and environmental pollution, introducing regional integrated energy system (RIES) into the electric power system is an important method to improve the proportion of clean energy in the terminal and energy efficiency. In order to realize the low-carbon economic operation of RIES, this paper firstly built the basic structural model of RIES. Furthermore, fully considering the governance cost of the carbon dioxide emissions of RIES, this paper constructed the mathematical model of RIES’ operation strategy with the lowest daily operation cost as the objective function, and then established the Markov decision process (MDP) problem of the model and introduced improved Q learning algorithm to seek the optimal operation strategy of RIES. The simulation results shown that the proposed model can realize the multi-energy complementation of RIES and the low-carbon economic operation of RIES on the basis of satisfying the balance of supply and demand, and ultimately realize the efficient and flexible use of energy.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-11-05
  • 最后修改日期:2021-04-16
  • 录用日期:2021-04-30
  • 在线发布日期:
  • 出版日期: