@article{Cheng2026, 
author = {Liangcheng Cheng and Jiahao Yan and Jianguo Yao and Shengchun Yang and Wenbo Mao and Kedong Zhu},
title = {Real-time Dispatch via Expert Knowledge Driven Deep Reinforcement Learning},
year = {2026},
journal = {CSEE Journal of Power and Energy Systems},
volume = {12},
number = {5},
pages = {2295-2307},
keywords = {Deep reinforcement learning, expert knowledge, real-time dispatch, regularization terms, twin delayed deep deterministic policy gradient},
url = {https://www.sciopen.com/article/10.17775/CSEEJPES.2022.03010},
doi = {10.17775/CSEEJPES.2022.03010},
abstract = {Power system real-time dispatch (RTD) problem optimizes generator outputs considering operational constraints and high-dimensional system information such as nodal loads and network topology. Conventional deep reinforcement learning methods aim to find optimal dispatch decisions through random exploration and lead to low computational efficiency. In this paper, we decompose RTD into three subproblems, namely unit commitment, power adjustment and voltage adjustment. A reinforcement agent is constructed using an expert knowledge-based twin delayed deep deterministic policy gradient algorithm (EK-TD3) to give power adjustment decisions, while unit commitment and voltage adjustment decisions are based on capacity-rules and volt-var sensitivity rules, respectively. Regularization terms based on expert knowledge are introduced to guide exploration of the agent, including generation-load mismatch, midpoint-maintaining rule of balance generator, renewable energy consumption rate and reserve capacity availability. Weight of different regularization terms can be adjusted periodically to reflect priority of dispatch objectives. The proposed method is tested on the State Grid 126-bus system (SG-126). Results prove the proposed method has better convergence performance compared with the conventional deep reinforcement learning method, enabling its application in large-scale power systems.}
}