A Novel Data-driven Excitation Control for the MPPT of Wound Rotor Synchronous Generator based Wind Turbine

This paper proposes an integral reinforcement learning (IRL)-based excitation control for the maximum power point tracking (MPPT) of wound rotor synchronous generator (WRSG)-based wind turbines. The proposed method produces superior dynamic performance over the conventional wind turbine MPPT excitation control in the presence of wind speed variations and grid disturbances. Moreover, its data-driven nature makes the proposed method independent of the system mathematical model, indicating very strong parameter robustness. Additionally, the proposed method possesses a very low computational complexity, which is desirable for real-time applications. The effectiveness of the proposed algorithm is verified by simulation results.