电力系统自动化2024，Vol.48Issue(1)：67-76,10.DOI:10.7500/AEPS20230426003
基于分层深度强化学习的分布式能源系统多能协同优化方法
Multi-energy Collaborative Optimization Method for Distributed Energy Systems Based on Hierarchical Deep Reinforcement Learning
摘要
Abstract
The multi-energy collaborative operation of distributed energy systems is of great significance for promoting the consumption of renewable energy.However,the uncertainty of sources and loads in distributed energy systems,as well as the spatiotemporal differences in heterogeneous energy networks,pose significant challenges to the optimization problem of multi-energy collaboration.A two-stage multi-energy collaborative optimization model for distributed energy systems is proposed to address this issue.A two-stage decoupling decision-making approach of long-time scale control and short-time scale control is adopted,thereby achieving sequential decision-making for composite spaces with different time response characteristics.Subsequently,in the face of high-dimensional composite search space and source-load uncertainty factors,a deep reinforcement learning model free solution is adopted,and a novel hierarchical deep reinforcement learning algorithm is proposed for solving.The effectiveness and superiority of the proposed model and solving method are verified through numerical simulations.关键词
分布式能源系统/新能源/多能协同/序贯决策/深度强化学习Key words
distributed energy system/renewable energy/multi-energy collaboration/sequential decision-making/deep reinforcement learning引用本文复制引用
王磊,胡国,吴海,谭阔,周成,朱亚军..基于分层深度强化学习的分布式能源系统多能协同优化方法[J].电力系统自动化,2024,48(1):67-76,10.基金项目
国家电网公司科技项目(5400-202233168A-1-1-ZN). This work is supported by State Grid Corporation of China(No.5400-202233168A-1-1-ZN). （5400-202233168A-1-1-ZN）
