| 引用本文: | 徐博涵,向 月,潘 力,等.基于深度强化学习的含高比例可再生能源配电网
就地分散式电压管控方法[J].电力系统保护与控制,2022,50(22):100-110.[点击复制] |
| XU Bohan,XIANG Yue,PAN Li,et al.Local decentralized voltage management of a distribution network with a high proportion ofrenewable energy based on deep reinforcement learning[J].Power System Protection and Control,2022,50(22):100-110[点击复制] |
|
| 摘要: |
| 含有可再生能源并网的区域电网存在通信条件差、量测设备不足、不同节点的电压管控设备难以协同等问题，因此提出一种基于深度强化学习的分散式就地电压管控方法。该方法首先将缺少量测数据的电压管控问题转化为部分可观的马尔科夫决策问题，构建了以网络损耗最小为优化目标的多智能体分散式电压管控框架。然后采用多智能体深度确定性策略梯度算法对智能体进行离线训练，并使用训练完成的智能体进行在线电压管控。最后，基于改进的IEEE33节点系统进行了算例仿真和分析。结果表明，各智能体可以根据各自节点的电气信息求解出近似的全局最优解。 |
| 关键词: 多智能体 电压管控 量测数据不足 多智能体深度确定性策略梯度算法 |
| DOI：DOI:?10.19783/j.cnki.pspc.220050 |
| 投稿时间：2022-02-12修订日期：2022-03-31 |
| 基金项目:国家电网科技项目资助“基于群体智能的能源互联网多源协同运行关键技术研究”(SGTJDK00DWJS2100039) |
|
| Local decentralized voltage management of a distribution network with a high proportion ofrenewable energy based on deep reinforcement learning |
| XU Bohan,XIANG Yue,PAN Li,FANG Mengqiu,PENG Guangbo,LIU Youbo,LIU Junyo |
| (College of Electrical Engineering, Sichuan University, Chengdu 610065, China) |
| Abstract: |
| A multi-agent decentralized local voltage control method based on the deep reinforcement learning is proposed. This is needed because there are some problems in the regional grid with renewable energy, such as poor communication conditions, insufficient measurement equipment, and difficult coordination of voltage control equipment at different nodes. First, this method transforms the voltage control problem lacking measurement data into a partial observable Markov decision problem, and a multi-agent decentralized voltage control framework with the optimization goal of minimizing network loss is constructed. Then, a multi-agent deep deterministic policy gradient algorithm is used to train the agents offline, and the trained agents are used for online voltage control. Finally, an example is simulated and analyzed based on the improved IEEE33 bus system. The results show that each agent can solve the approximate global optimal solution according to the electrical information of its own node.
This work is supported by the Science and Technology Project of State Grid Corporation of China (No. SGTJDK00DWJS2100039). |
| Key words: multi-agent voltage control insufficient measurement data multi-agent deep deterministic policy gradient algorithm |
