Workshop:AI4S: Workshop on Artificial Intelligence and Machine Learning for Scientific Applications
Authors: Xiumin Shang (Global Energy Interconnection Research Institute North America (GEIRI); University of California, Merced); Lin Ye and Jing Zhang (Zhejiang Electric Power Company); Jingping Yang, Jianping Xu, and Qin Lyu (Jinhua Electric Power Company); and Ruisheng Diao (Global Energy Interconnection Research Institute North America (GEIRI))
Abstract: With the ever-increasing stochastic and dynamic behavior observed in today’s bulk power systems, securely and economically planning future operational scenarios that meet all reliability standards under uncertainties becomes a challenging computational task, which typically involves searching feasible and suboptimal solutions in a highly dimensional space via massive numerical simulations. This paper presents a novel approach to achieving this goal by adopting the state-of-the-art reinforcement learning algorithm, soft actor critic (SAC). First, the optimization problem of finding feasible solutions under uncertainties is formulated as Markov decision process. Second, a general and flexible framework is developed to train SAC agents by adjusting generator active power outputs in searching feasible operating conditions. A software prototype is developed that verifies the effectiveness of the proposed approach via numerical studies conducted on the future planning cases of the SGCC Zhejiang Electric Power Company.