基于安全深度强化学习的电网有功频率协同优化控制

周毅, 周良才, 史迪, 赵小英, 闪鑫

Coordinated Active Power-Frequency Control Based on Safe Deep Reinforcement Learning

ZHOU Yi, ZHOU Liangcai, SHI Di, ZHAO Xiaoying, SHAN Xin

图3 训练阶段智能体平均回报值

Fig.3 Average total return in training stage