Power System Load Frequency Active Disturbance Rejection Control via Reinforcement Learning-Based Memetic Particle Swarm Optimization

Load frequency control (LFC) is necessary to guarantee the safe operation of power systems. Aiming at and stability problems caused by load disturbances in interconnected systems, active disturbance rejection (ADRC) was designed. There are eight parameters that need be adjusted for an ADRC, which challenging adjust manually, thus limiting development this approach industrial applications. Regardless theory or application, there still no unified efficient parameter optimization method. The traditional particle swarm (PSO) algorithm suffers from premature convergence a high computational cost. Therefore, paper, we utilize improved PSO algorithm, reinforcement-learning-based memetic (RLMPSO), tuning ADRC obtain better performance controlled system. Finally, highlight advantages proposed RLMPSO-ADRC method prove its superiority, results were compared with other algorithms both non-reheat two-area thermal system non-linear governor dead band (GDB) generation rate constraint (GRC). Moreover, robustness tested simulations perturbations different working conditions. simulation showed can meet demand deviation stabilize 0 LFC higher performance, it worthy popularization application.