半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于深度强化学习的配电网多时间尺度在线无功优化
作者:
作者单位:

1.上海电力大学自动化工程学院,上海市 200090;2.上海市智能电网需求响应重点实验室,上海市 200063;3.上海电力大学电气工程学院,上海市 200090

摘要:

含分布式电源的配电网存在潮流建模不精确、通信能力不强、各无功补偿设备难以协调等问题,给配电网在线无功优化带来了挑战。文中采用深度强化学习方法,提出了一种多时间尺度配电网在线无功优化运行方案。该方案将配电网在线无功优化问题转化为马尔可夫决策过程。鉴于不同无功补偿设备的调节速度不同,设计2个时间尺度分别对离散调节设备和连续调节设备进行优化配置。该方案能够实时追踪配电网状态,在线决策无功调节设备的优化方案,且不依赖精确的潮流模型,适用于复杂多变、通信能力不强的部分可观测配电网。最后,通过算例验证了所提方法的有效性和鲁棒性。

关键词:

基金项目:

国家自然科学基金青年计划(51607111);上海市科技创新行动计划资助项目(18DZ1203502、19DZ1205700)。

通信作者:

作者简介:


Multi-time-scale Online Optimization for Reactive Power of Distribution network Based on Deep Reinforcement Learning
Author:
Affiliation:

1.College of Automation Engineering, Shanghai University of Electrical Power, Shanghai 200090, China;2.Shanghai Key Laboratory of Smart Grid Demand Response, Shanghai 200063, China;3.College of Electrical Engineering, Shanghai University of Electrical Power, Shanghai 200090, China

Abstract:

The distribution network with distributed generators has problems such as inaccurate power flow modeling, weak communication capabilities, and difficulty in coordination of various reactive power compensation equipment. The problems bring challenges to the online optimization for reactive power of the distribution network. This paper proposes a multi-time-scale online optimization for reactive power of the distribution network based on the method of deep reinforcement learning (DRL). The scheme converts the problem of the online optimization for reactive power of the distribution network into a Markov decision process (MDP). In view of the different adjustment speeds of different reactive power compensation equipment, two time scales are designed to optimize the configuration of the discrete adjustment equipment and the continuous adjustment equipment. This scheme can track the status of the distribution network in real time, make online decisions about the optimization for reactive power regulation equipment, and does not rely on accurate power flow models. It is suitable for some observable distribution networks that are complex and changeable and have poor communication capabilities. Finally, a numerical example verifies the effectiveness and robustness of the proposed method.

Keywords:

Foundation:
This work is supported by National Natural Science Foundation of China (No. 51607111) and Shanghai Science and Technology Innovation Action Plan (No. 18DZ1203502, No. 19DZ1205700).
引用本文
[1]倪爽,崔承刚,杨宁,等.基于深度强化学习的配电网多时间尺度在线无功优化[J/OL].电力系统自动化,http://doi. org/10.7500/AEPS20200830003.
NI Shuang, CUI Chenggang, YANG Ning, et al. Multi-time-scale Online Optimization for Reactive Power of Distribution network Based on Deep Reinforcement Learning[J/OL]. Automation of Electric Power Systems, http://doi. org/10.7500/AEPS20200830003.
复制
分享
历史
  • 收稿日期:2020-08-30
  • 最后修改日期:2021-02-21
  • 录用日期:2020-12-12
  • 在线发布日期:
  • 出版日期:
相关附件