An enhanced uncertainty and disturbance estimator based on Bi-LSTM-OTC-LADRC of grid-connected wind energy conversion system

Power restriction and load reduction are key challenges for large wind turbines in high wind speeds. Controller design is crucial to handle system nonlinearities and unpredictable wind for stable, eco-friendly power generation without oscillations. In this context, this study introduces both linear and nonlinear control algorithms that might be implemented on a grid-connected wind energy conversion system (G-CWECS) to optimize the extraction of the global maximum power point (GMPP) and improve active and reactive power regulation. The foundation of these strategies lies in linear active disturbance rejection control (LADRC), which is well-known for its capability to handle uncertainties and disturbances, relying on its observer. The current-based bidirectional LSTM (CBi-LSTM) and optimum torque control (OTC) MPPT method integrated with LADRC are employed to extract GMP from WECS. A powerful metaheuristic technique, named catch fish algorithm (CFA), is utilized to update the Bi-LSTM weights. The LADRC approach is applied to regulate both active and reactive power by controlling grid currents, ensuring a unity power factor. Matlab simulation and Hardware-In-the-Loop (HIL) experiment are carried out to verify the feasibility of the implementation. Comparing with well-known-MPPT methods, the output outcomes prove the efficiency of the recommended Bi-LSTM-OTC-LADRC regarding GMPP extraction during wind speed variation. Additionally, it's proved that the proposed LADRC approach is robustness in terms of managing the uncertainties and disturbances compared to PI, PID and SMC controllers.