Hybrid Imitation Learning for Real-Time Service Restoration in Resilient Distribution Systems
This work aims to improve the real-time self-healing capability of distribution systems for grid operators by enabling faster and more robust service restoration under various disturbances.
This paper addresses the challenge of real-time service restoration in resilient distribution systems by proposing an imitation learning (IL) framework. The framework trains intelligent agents to perform restorative actions, including network reconfiguration and reactive power dispatch, to handle complex N-k scenarios.
Self-healing capability is one of the most critical factors for a resilient distribution system, which requires intelligent agents to automatically perform restorative actions online, including network reconfiguration and reactive power dispatch. These agents should be equipped with a predesigned decision policy to meet real-time requirements and handle highly complex $N-k$ scenarios. The disturbance randomness hampers the application of exploration-dominant algorithms like traditional reinforcement learning (RL), and the agent training problem under $N-k$ scenarios has not been thoroughly solved. In this paper, we propose the imitation learning (IL) framework to train such policies, where the agent will interact with an expert to learn its optimal policy, and therefore significantly improve the training efficiency compared with the RL methods. To handle tie-line operations and reactive power dispatch simultaneously, we design a hybrid policy network for such a discrete-continuous hybrid action space. We employ the 33-node system under $N-k$ disturbances to verify the proposed framework.