计算机应用与软件2024，Vol.41Issue(11)：160-167,8.DOI:10.3969/j.issn.1000-386x.2024.11.022
基于DRL和智能探索机制的CMPLDWG参数辨识
PARAMETER IDENTIFICATION OF CMPLDWG BASED ON DRL AND INTELLIGENT EXPLORATION MECHANISM
摘要
Abstract
In order to effectively deal with the inherent high nonlinearity and non-convexity of the distributed generation composite load system and improve the identification accuracy and efficiency of the model,a parameter identification method based on deep reinforcement learning and intelligent exploration mechanism is proposed.The parameter sensitivity analysis was carried out by using the data-driven feature kernel Lasso method,and the sensitivity weights reflecting the contribution of parameters to the model dynamics were obtained.The improved deep reinforcement learning with intelligent detection function was used for parameter identification.The numerical experiment results show that the method has high identification accuracy,can effectively avoid falling into local optimum,and has fast learning speed.关键词
参数辨识/复合负载模型/深度强化学习/灵敏度权值Key words
Parameter identification/Composite load model/Deep reinforcement learning/Sensitivity weight分类
信息技术与安全科学引用本文复制引用
王新刚,朱文君,陈金涛,盛青..基于DRL和智能探索机制的CMPLDWG参数辨识[J].计算机应用与软件,2024,41(11):160-167,8.基金项目
国家电网公司总部科技项目(52094016001Z). （52094016001Z）
