浙江电力2025，Vol.44Issue(5)：101-111,11.DOI:10.19585/j.zjdl.202505010
基于深度强化学习的多能流建筑综合能源系统优化调度
Optimal scheduling of BIES with multi-energy flow coupling based on deep RL
摘要
Abstract
Building integrated energy systems(BIESs)can enhance energy efficiency ratio(EER)and reduce car-bon emissions while meeting diverse user-side load demands.To further improve the energy dispatch capability of BIES,this paper proposes a low-carbon economic and optimal dispatch method for BIES with multi-energy flow cou-pling based on deep reinforcement learning(deep RL).Firstly,a mathematical model of a photovoltaic-storage inte-grated BIES with multi-energy flow coupling is established to fully characterize energy interaction and coupling char-acteristics.Secondly,the state space,action space,and reward function for the operational dispatch strategy are de-signed using deep RL,and a low-carbon economic and optimal dispatch framework is constructed using the soft actor-critic(SAC)algorithm.Finally,the proposed method is validated in typical daily load scenarios in summer and winter.Results demonstrate that,compared to similar methods,the proposed method achieves faster conver-gence,more stable optimization effects,and effectively reduces both daily energy costs and carbon emission costs in IES operations.关键词
深度强化学习/综合能源系统/调度优化/碳排放Key words
deep RL/IES/scheduling optimization/carbon emission引用本文复制引用
夏旭华,杨建迪,施永涛..基于深度强化学习的多能流建筑综合能源系统优化调度[J].浙江电力,2025,44(5):101-111,11.基金项目
浙江省重点研发计划项目(2024C01018) （2024C01018）
