Load Frequency Control of Two-area Power System Using an Actor-Critic Reinforcement Learning Method-based Adaptive PID Controller

In this paper, an actor-critic reinforcement learning (RL) method-based adaptive proportional-integral-derivative (PID) control strategy is proposed for the load frequency control (LFC) of a two-area power system. The parameters of the PID controller are updated through an actor-critic policy in real-time. This actor-critic method implements radial basis function (RBF) based neural network for both actor and critic networks. The parameters of the neural network are updated using gradient descent method. A numerical case study is demonstrated with proper illustration and analysis of the results.