TD3-Based Model-Free Adaptive Control for Shunt Active Power Filters Under Composite Disturbances

The increasing penetration of nonlinear loads aggravates grid harmonic distortion and imposes higher requirements on the control performance of the shunt active power filter (SAPF). To address the problems of fixed parameters in conventional PI controllers and the dependence of existing improved methods on accurate models with relatively high computational complexity, this paper proposes a TD3-based model-free adaptive control method for online coordinated tuning of dual-loop PI parameters in the SAPF system. The proposed method dynamically adjusts PI parameters through agent–environment interaction without requiring an accurate system model or a complex control structure. Simulation results show that the proposed strategy outperforms fixed-parameter PI control, PI-SMC, and DDPG methods in both steady-state and dynamic performance, and maintains good control performance under unseen composite disturbances such as capacitive inrush and load variation. RT-LAB-based hardware-in-the-loop (HIL) validation further demonstrates that the proposed method can achieve effective harmonic compensation and DC-link voltage regulation on a real-time simulation platform. Meanwhile, during online deployment, only Actor-network forward inference is required to update the PI parameters, indicating a low additional computational burden and engineering implementation potential for SAPF real-time control systems.