Voltage Optimal Control of Distribution Network Based on Deep Reinforcement Learning

被引：0
|
作者：
Quan H. [1 ]
Peng X. [1 ]
Liu H. [1 ]
Zhou P. [1 ]
Wu Z. [1 ]
Su H. [1 ]
机构：
[1] School of Automation, Guangdong University of Technology, Guangdong Province, Guangzhou
来源：
Dianwang Jishu/Power System Technology | 2023年 / 47卷 / 05期
基金：
中国国家自然科学基金;
关键词：
data-driven; Markov decision process; multi-agent deep reinforcement learning; photovoltaic inverter; voltage optimal control of distribution network;
D O I：
10.13335/j.1000-3673.pst.2022.1472
中图分类号：
学科分类号：
摘要：
The access of large-scale distributed generation makes the distribution network voltage optimization control strategy different from the traditional distribution network. Aiming at the problem of lack of coordination between photovoltaic inverter voltage regulation in local control, this paper proposes a voltage control method of distribution network based on multi-agent deep reinforcement learning. Firstly, the partially observable Markov decision process is designed according to the voltage control model, and then the multi-agent twin delayed deep deterministic policy gradient algorithm is used to solve it, and the coordinated reactive power control of PV inverters is realized according to the framework of centralized training and decentralized execution. The method can make intelligent decisions on the amount of reactive power regulation for each inverter, generating the real-time voltage control strategy according to the random change of generation and load. It has good real-time performance and control economy. Finally, the effectiveness of the proposed method is verified by simulation examples. © 2023 Power System Technology Press. All rights reserved.
引用
收藏
页码：2029 / 2038
页数：9
相关论文
共 28 条
  • [1] XU Xiaoyan, HUANG Yuehui, LIU Chun, Influence of distributed photovoltaic generation on voltage in distribution network and solution of voltage beyond limits[J], Power System Technology, 34, 10, pp. 140-146, (2010)
  • [2] WECKX S, DRIESEN J．, Optimal local reactive power control by PV inverters[J], IEEE Transactions on Sustainable Energy, 7, 4, pp. 1624-1633, (2016)
  • [3] CAI Yongxiang, TANG Wei, XU Ouyang, Review of voltage control research in LV distribution network with high proportion of residential PVs[J], Power System Technology, 42, 1, pp. 220-229, (2018)
  • [4] BLETTERIE B, KADAM S, BOLGARYN R, Voltage control with PV inverters in low voltage networks-in depth analysis of different concepts and parameterization criteria[J], IEEE Transactions on Power Systems, 32, 1, pp. 177-185, (2017)
  • [5] GU Jie, MENG Lu, ZHU Tongtong, Data-driven optimization for reactive power operation in source distributionnetwork without accurate modeling[J], Electric Power Automation Equipment, 41, 1, pp. 1-8, (2021)
  • [6] YU Zhipeng, TANG Yi, DAI Jianfeng, Voltage/var control strategy of PV plant based on adaptive adjustment of active power[J], Power System Technology, 44, 5, pp. 1900-1907, (2020)
  • [7] CAO Di, Weihao HU, ZHAO Junbo, Reinforcement learning and its applications in modern power and energy systems ： a review[J], Journal of Modern Power Systems and Clean Energy, 8, 6, pp. 1029-1042, (2020)
  • [8] MNIH V，, KAVUKCUOGLU K, SILVER D, Human-level control through deep reinforcement learning[J], Nature, 518, 7540, pp. 529-533, (2015)
  • [9] ZHANG Zidong, ZHANG Dongxia, QIU R C．, Deep reinforcement learning for power system applications：an overview[J], CSEE Journal of Power and Energy Systems, 6, 1, pp. 213-225, (2020)
  • [10] Quan LIU, ZHAI Jianwei, ZHANG Zongzhang, A survey on deep reinforcement learning[J], Chinese Journal of Computers, 41, 1, pp. 1-27, (2018)
123