Resilient Distribution Networks by Microgrid Formation Using Deep Reinforcement Learning

Abstract

Resilience becomes vital for power grids facing the increasingly frequent extreme weather events. Microgrid formation is a promising way to achieve resilient distribution networks (RDN) when the utility power is unavailable. This paper proposes a RDN-oriented microgrid formation (RoMF) method based on the deep reinforcement learning (DRL) technique, which integrates the OpenDSS as an interaction object and searches for optimal control policies in a model-free fashion. Specifically, we formulate the microgrid formation problem as a Markov decision process, taking into account complex factors such as unbalanced three-phase power flow and microgrid operation constraints. Next, a simulator-based RoMF environment is constructed and integrated into the OpenAI Gym, providing a standard agent-environment interface for applying DRL algorithms. Then, the deep Q-network is used to search for optimal microgrid formation strategies, and an offline-training and online-application framework of the DRL-based RoMF is given. Finally, extensive numerical results validate the effectiveness of our proposed method.