针对主动配电网电压优化控制中模型不确定性和通信代价大的问题,提出了一种基于灵敏度矩阵安全的多智能体深度强化学习(SMS-MADRL)算法。该算法利用安全深度强化学习,应对主动配电网的固有不确定性,并采用多智能体结构实现通信代价较小的分布式控制。首先,将电压优化控制问题描述为受约束的马尔可夫博弈(CMG);然后,对无功功率进行适当修改,通过分析节点电压的变化得到灵敏度矩阵,进而与主动配电网环境进行交互,训练出若干可以独立给出最优无功功率指令的智能体。与现有多智能体深度强化学习算法相比,该算法的优点在于给智能体的动作网络增添了基于灵敏度矩阵的安全层,在智能体的训练和执行阶段保证了主动配电网的电压安全性。在IEEE 33节点系统上的仿真结果表明:所提出的算法不仅能够满足电压约束,而且相较于多智能体深度确定性策略梯度(MADDPG)算法,网络损耗减少了4.18%
控制代价减少了70.5%。该研究可为主动配电网的电压优化控制提供理论基础。
曹迪.主动配电网电压控制策略研究[D].电子科技大学,2021(03).
Gao Yuanqi,Yu Nanpeng.Model-augmented safe reinforcement learning for Volt-VAR control in power distribution networks[J].Applied Energy,2022.
Zhang Xi,Liu Youbo,Duan Jiajun,Qiu Gao,Liu Tingjian,Liu Junyong.DDPG-Based Multi-Agent Framework for SVC Tuning in Urban Power Grid With Renewable Energy Resources[J].IEEE TRANSACTIONS ON POWER SYSTEMS,2021.
Liu Hangyue,Zhang Cuo,Chai Qingmian,Meng Ke,Guo Qinglai,Dong Zhao Yang.Robust Regional Coordination of Inverter-Based Volt/Var Control via Multi-Agent Deep Reinforcement Learning[J].IEEE TRANSACTIONS ON SMART GRID,2021.
Liu Haotian,Wu Wenchuan.Online Multi-Agent Reinforcement Learning for Decentralized Inverter-Based Volt-VAR Control[J].IEEE TRANSACTIONS ON SMART GRID,2021.
Liu Yibin,Liang Deliang,Kou Peng,Zhang Mingkang,Cai Shengliang,Zhou Kun,Liang Yang,Chen Qixu,Yang Chuankai.Compound Control System of Hybrid Distribution Transformer[J].IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS,2020.
Peng Kou,Deliang Liang,Chen Wang,Zihao Wu,Lin Gao.Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks[J].Applied Energy,2020.
Di Cao,Weihao Hu,Junbo Zhao,Qi Huang,Zhe Chen,Frede Blaabjerg.A Multi-agent Deep Reinforcement Learning Based Voltage Regulation using Coordinated PV Inverters[J].IEEE Transactions on Power Systems,2020.
Sun Hongbin,Guo Qinglai,Qi Junjian,Ajjarapu Venkataramana,Bravo Richard,Chow Joe,Li Zhengshuo,Moghe Rohit,Nasr Azadani Ehsan,Tamrakar Ujjwol,Taranto Glauco N.,Tonkoski Reinaldo,Valverde Gustavo,Wu Qiuwei,Yang Guangya.Review of Challenges and Research Opportunities for Voltage Control in Smart Grids[J].IEEE Transactions on Power Systems,2019.
Christakou Konstantina,Paolone Mario,Abur Ali.Voltage Control in Active Distribution Networks Under Uncertainty in the System Model: A Robust Optimization Approach[J].IEEE Transactions on Smart Grid,2018.
Bidgoli Hamid Soleimani,Van Cutsem Thierry.Combined Local and Centralized Voltage Control in Active Distribution Networks[J].IEEE Transactions on Power Systems,2018.
Gill, S.,Kockar, I.,Ault, G.W..Dynamic Optimal Power Flow for Active Distribution Networks[J].IEEE Transactions on Power Systems: A Publication of the Power Engineering Society,2014.
Baran Mesut E.,Wu Felix F..Network Reconfiguration in Distribution Systems for Loss Reduction and Load Balancing[J].IEEE Power Engineering Review,1989(4).
汤涌,姚伟,王宏志,王灿,郭强,王甜婧,黄彦浩.电网仿真分析与决策的人工智能方法[J].中国电机工程学报,2022(15).
倪爽,崔承刚,杨宁,陈辉,奚培锋,李振坤.基于深度强化学习的配电网多时间尺度在线无功优化[J].电力系统自动化,2021(10).
高荣,寇鹏,梁得亮,柳轶彬,吴子豪.含混合式配电变压器的主动配电网电压鲁棒模型预测控制[J].中国电机工程学报,2020(07).
李琦,乔颖,张宇精.配电网持续无功优化的深度强化学习方法[J].电网技术,2020(04).
王秀丽,张择策,侯雨伸.主动配电网多维度静态安全评估[J].西安交通大学学报,2016(08).
徐志成,赵波,丁明,周金辉,韦立坤.基于电压灵敏度的配电网光伏消纳能力随机场景模拟及逆变器控制参数优化整定[J].中国电机工程学报,2016(06).
刘一兵,吴文传,张伯明,李正烁,巨云涛.基于混合整数二阶锥规划的三相有源配电网无功优化[J].电力系统自动化,2014(15).
谷永刚,肖凯,夏经德,赵登福.利用增量二次规划和启发式方法的电力系统动态无功优化[J].西安交通大学学报,2010(08).
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621