基于强化学习的负荷聚合商电价激励响应调频中的博弈与策略分析
DOI:
作者:
作者单位:

1.合肥工业大学计算机与信息学院;2.国网安徽省电力有限公司;3.合肥工业大学电气与自动化工程学院

作者简介:

通讯作者:

中图分类号:

TM732

基金项目:

安徽省自然科学基金资助项目(2208085UD06)


Game and Strategy Analysis of Power Price Incentive Response Frequency Modulation in Load Aggregation Based on Reinforcement Learning
Author:
Affiliation:

1.School of Computer Science and Information Engineering;2.State Grid Anhui Electric Power Company;3.School of Electrical Engineering and Automation, Hefei University of Technology

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:

    为了解决分布式负荷响应调频指令中的效率问题,本文提出了一种基于强化学习的负荷聚合商电价激励响应调频创新策略,在该策略中,构建聚合商和负荷集群博弈模型,聚合商根据调频指令和激励电价策略调整激励电价,而负荷根据自身用电成本调节用电功率,灵活地响应调频指令,采用多智能体软演员批评家(MASAC,multi-agent soft actor-critic)算法求解。结果表明电价激励方法可以使得负荷有效响应调频指令,通过MASAC算法不仅可以优化决策过程,还能有效降低运算复杂性,实现高效的动态调节。可见,该方法为电力系统的频率调节提供了一种有效的解决方案,具有重要的理论意义和实际应用价值。

    Abstract:

    In order to solve the efficiency issues in distributed load responses to frequency regulation commands, this paper introduces an innovative strategy based on reinforcement learning for load aggregators' pricing incentives in response to frequency commands. Within this strategy, a game-theoretic model between the load aggregators and load clusters was constructed, and the load aggregators adjust incentive prices based on frequency commands and their pricing strategies, while loads adjust their power consumption based on their own electricity costs to flexibly respond to the frequency commands. The Multi-Agent Soft Actor-Critic (MASAC) algorithm was used to investigate the solution. The results show that the pricing incentive method enables effective load response to frequency commands, and the use of the MASAC algorithm not only optimizes the decision-making process but also significantly reduces computational complexity, achieving efficient dynamic adjustment. It is concluded that this method provides an effective solution for frequency regulation in power systems, offering significant theoretical significance and practical value.

    参考文献
    相似文献
    引证文献
引用本文

吴静,程文娟,梁肖,等. 基于强化学习的负荷聚合商电价激励响应调频中的博弈与策略分析[J]. 科学技术与工程, , ():

复制
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:2024-04-09
  • 最后修改日期:2024-05-18
  • 录用日期:2024-05-22
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注