中国电机工程学报2018，Vol.38Issue(1)：109-119,后插11,12.DOI:10.13334/j.0258-8013.pcsee.171747
基于深度强化学习的电网紧急控制策略研究
A Decision Making Strategy for Generating Unit Tripping Under Emergency Circumstances Based on Deep Reinforcement Learning
摘要
Abstract
This paper proposed a kind of method for improving generating unit tripping strategy using deep reinforcement learning. The method is data driven, only power gird environmental information is needed. Firstly, basic principle and framework of reinforcement learning was briefly introduced and Q-Learning was expounded in detail. Secondly, the fundamental idea of deep learning was introduced. Then the deep convolutional neural network was used to extract features for power system during transient process. Thirdly, the deep reinforcement learning model was constructed by combining deep learning with reinforcement learning, and the double Q model and dueling Q model was used to improve the performance about Q-Learning and calculate Q value, and the control strategy can be obtained by comparing Q value. Finally, case study based on IEEE 39 node system validates the proposed approach.关键词
深度强化学习/卷积神经网络/数据驱动/决策控制/人工智能Key words
deep reinforcement learning/convolutional neural network/data driven/decision control/artificial intelligence分类
信息技术与安全科学引用本文复制引用
刘威,张东霞,王新迎,侯金秀,刘丽平..基于深度强化学习的电网紧急控制策略研究[J].中国电机工程学报,2018,38(1):109-119,后插11,12.基金项目
国家自然科学基金资助项目(61703379). Project Supported by National Natural Science Foundation of China (61703379). （61703379）
