用强化学习解决配电网电压无功控制难题，兼顾安全与效率

This paper proposes a data-driven solution for Volt-VAR control problem in active distribution system. As distribution system models are always inaccurate and incomplete, it is quite difficult to solve the problem. To handle with this dilemma, this paper formulates the Volt-VAR control problem as a constrained Markov decision process (CMDP). By synergistically combining the augmented Lagrangian method and soft actor critic algorithm, a novel safe off-policy reinforcement learning (RL) approach is proposed in this paper to solve the CMDP. The actor network is updated in a policy gradient manner with the Lagrangian value function. A double-critics network is adopted to synchronously estimate the action-value function to avoid overestimation bias. The proposed algorithm does not require strong convexity guarantee of examined problems and is sample efficient. A two-stage strategy is adopted for offline training and online execution, so the accurate distribution system model is no longer needed. To achieve scalability, a centralized training distributed execution strategy is adopted for a multi-agent framework, which enables a decentralized Volt-VAR control for large-scale distribution system. Comprehensive numerical experiments with real-world electricity data demonstrate that our proposed algorithm can achieve high solution optimality and constraints compliance.