基于状态降维的快速强化学习电力网络系统控制  

FAST REINFORCEMENT LEARNING POWER NETWORK SYSTEM CONTROL BASED ON STATE DIMENSION REDUCTION

作　　者：童涛 陈海宾 甄昊涵 沈华 林文浩 Tong Tao;Chen Haibin;Zhen Haohan;Shen Hua;Lin Wenhao(State Grid Shanghai Electric Power Company Electric Power Research Institute,Shanghai 200051,China)

机构地区：[1]国网上海市电力公司电力科学研究院,上海200051

出　　处：《计算机应用与软件》2025年第3期92-101,共10页Computer Applications and Software

基　　金：国家电网公司总部科技项目(52094017001X)。

摘　　要：为了避免大规模电力网络系统控制的维数灾,提升其可控性,提出一种基于状态降维的快速强化学习方法。通过投影矩阵投影测量状态来构造压缩状态向量,捕获开环网络模型的主要可控子空间,从而利用网络可控性的低秩属性避免了维数灾难;提出降维状态深度学习控制器,从而使结果成本接近最优LQR成本。通过一致性网络系统和IEEE广域控制实验结果,验证了提出的方法能够显著加快学习时间,同时保证了较好的优化性能。In order to avoid dimension disaster and improve controllability,a fast reinforcement learning control method for large-scale power network system based on state dimension reduction is proposed.The compressed state vector was constructed by projecting the measured state through the projection matrix,and the main controllable subspace of the open-loop network model was captured,so the dimension disaster was avoided by using the low rank attribute of network controllability.A reduced dimension state depth learning controller was proposed to make the result cost close to the optimal LQR cost.The experimental results of consensus network system and IEEE wide area control show that the proposed method can significantly accelerate the learning time and ensure better sub-optimal performance.

关 键 词：状态降维 强化学习 网络系统 维数灾难 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]