现代电力2025，Vol.42Issue(2)：322-332,11.DOI:10.19725/j.cnki.1007-2322.2023.0026
基于改进深度确定性策略梯度算法的综合能源系统优化调度策略
Optimization Scheduling Strategies for Integrated Energy Systems Based on Improved Deep Deterministic Policy Gradient Algorithm
龚锦霞 1李琛舟 1柯慧2
作者信息
- 1. 上海电力大学电气工程学院,上海市杨浦区 200090
- 2. 上海电力设计院有限公司,上海市黄浦区 200025
- 折叠
摘要
Abstract
To address the issues of large decision space and difficulty in convergence in the optimization scheduling of in-tegrated energy systems,in this paper we propose an optimized scheduling strategy based on the improved deep deterministic policy gradient(DDPG)algorithm.The difficulty in conver-gence and even failure in optimization is solved by adding a second experience pool.In order to address the optimization scheduling challenge of integrated energy systems,the al-gorithm is optimized by improving the network parameter up-date process,resulting in an increase in the efficiency of the training process.In addition,the reward function is redesigned and a non-linear reward function is adopted to further improve the stability of the algorithm.Finally,an integrated energy sys-tem composed of photovoltaic,energy storage systems,refri-geration units,electric heating units and gas boilers is simu-lated,and the performance of the algorithm is compared before and after the improvement.The case study indicates that the op-timization scheduling strategy based on the improved deep de-terministic policy gradient algorithm exhibits excellent conver-gence,stability and high training efficiency.Moreover,it en-ables flexible and efficient scheduling of the integrated energy system.关键词
综合能源系统/DDPG算法/马尔可夫决策过程/深度强化学习Key words
integrated energy system/DDPG algorithm/Markov decision process/deep reinforcement learning分类
动力与电气工程引用本文复制引用
龚锦霞,李琛舟,柯慧..基于改进深度确定性策略梯度算法的综合能源系统优化调度策略[J].现代电力,2025,42(2):322-332,11.
