Control method of power grid topology structure based on reinforcement learning

Abstract

With the rapid development of renewable energy and power electronics technology, uncertainty, complexity and data accumulation in power system continue to increase. Traditional methods often encounter bottlenecks in solving operational optimization decision-making and control problems. The development of artificial intelligence technology provides new methods and means for solving the problem of intelligent control of power grid topology. The deep reinforcement learning (DRL) method is used to learn from the historical experience data of power grid topology control that can improve the control and decision-making and methods of system operating performance, and solve the huge variables in traditional models. Through the method in this paper, the DRL method can effectively improve the real-time optimization and control ability of the grid topology.