Reactive Power Optimization Based on Proximal Policy Optimization of Deep Reinforcement Learning

被引：0
|
作者：
Zahng P. [1 ]
Zhu Z. [1 ]
Xie H. [1 ]
机构：
[1] School of Electrical Engineering, Beijing Jiaotong University, Haidian District, Beijing
来源：
Dianwang Jishu/Power System Technology | 2023年 / 47卷 / 02期
关键词：
data driving; deep reinforcement learning; new power system; proximal policy optimization; reactive power optimization;
D O I：
10.13335/j.1000-3673.pst.2022.0728
中图分类号：
学科分类号：
摘要：
The fluctuations of renewable energies and loads pose a great challenge to reactive power optimization. Considering the time-varying characteristics of new energies and loads, the reactive power optimization problem is constructed as a reinforcement learning problem. The method of constraint-target division and target presupposition is proposed to design a reward function, and the proximal policy optimization algorithm is used to solve the reinforcement learning problem, getting the reactive power optimization policy. A case study is carried out with the modified IEEE39 system, and the results show that the proposed reward function can improve the convergence speed of the agent. The reactive power optimization strategy based on reinforcement learning is supirior to the traditional deterministic optimization algorithm in decision-making effects and decision-making time. © 2023 Power System Technology Press. All rights reserved.
引用
收藏
页码：562 / 570
页数：8
相关论文
共 35 条
  • [1] YU Juan, YAN Wei, XU Guoyu, A new model of reactive optimization based on predictor corrector primal dual interior point method[J], Proceedings of the CSEE, 25, 11, pp. 146-151, (2005)
  • [2] ZHAO Jingbo, WEI Zhinong, LIU Jiankun, Linearized dynamic optimal power flow model for power system[J], Automation of Electric Power Systems, 42, 20, pp. 86-92, (2018)
  • [3] XU Jianting, WANG Xiuying, LI Xingyuan, Successive quadratic programming method for voltage/reactive power optimization in power systems[J], Automation of Electric Power Systems, 25, 23, pp. 4-8, (2001)
  • [4] Zhu LUO, Optimal control of voltage and reactive power in power systems[J], Automation of Electric Power Systems, 12, 1, pp. 9-15, (1988)
  • [5] LAI Xiaowen, MA Xiaowei, BAI Yang, Dynamic reactive power optimization method based on mixed integer second-order cone programming[J], Automation of Electric Power Systems, 41, 17, pp. 37-42, (2017)
  • [6] GUO Qingyuan, WU Jiekang, MO Chao, A model for multi-objective coordination optimization of voltage and reactive power in distribution networks based on mixed integer second-order cone programming[J], Proceedings of the CSEE, 38, 5, pp. 1385-1396, (2018)
  • [7] ZHOU Xiaohua, LUO Wenguang, LIU Shengyong, Voltage control method of static var compensator based on adaptive dynamic programming[J], Power System Technology, 41, 3, pp. 895-900, (2017)
  • [8] SUN Tian, ZOU Peng, YANG Zhifang, A multi-stage solution approach for dynamic reactive power optimization[J], Power System Technology, 40, 6, pp. 1807-1813, (2016)
  • [9] HUANG Junhui, WANG Weiyuan, WANG Haiqian, Study of hybrid genetic algorithm and annealing algorithm on reactive power optimization and voltage control in AC/DC transmission system[J], Power System Protection and Control, 44, 10, pp. 37-43, (2016)
  • [10] ZHAO Kun, GENG Guangfei, Reactive power optimization of distribution network based on improved genetic algorithm[J], Power System Protection and Control, 35, 5, pp. 57-62, (2011)
1234