Learning-boosted intelligent frequency control of multi-area Markov jumping power system via multiplayer Stackelberg-Nash game

Abstract

This paper proposes an intelligent frequency control (IFC) scheme integrating multiple strategies, which aims to address the frequency control challenges of multi-area Markov jumping power systems (MMJPSs) under load fluctuations and external disturbances. Firstly, the Markov superposition technique is employed to conduct refined modeling on the system component matrices, precisely capturing the diversity of load operating states. Secondly, within the framework of the multiplayer Stackelberg-Nash game (MSNG), the load aggregator (LA) is set as the leader and the turbines in each area are regarded as the followers. By constructing the value functions of the leader and the followers, the dynamic process of hierarchical decision-making is elaborately depicted. Meanwhile, an adaptive event-triggered mechanism (AETM) is designed to alleviate the computational and communication burdens. On this basis, by combining the integral reinforcement learning (IRL) algorithm with the neural network (NN), the Hamilton-Jacobi-Bellman (HJB) equation based on the AETM is solved to obtain the approximately optimal control law and achieve the Stackelberg-Nash equilibrium (SNE). Utilizing Lyapunov stability theory, the uniform ultimate boundedness (UUB) of the system states and the NN weight errors is rigorously proved. Finally, comparative simulation results validate the effectiveness and practicality of the proposed method.