Optimised MPPT control using enhanced RNN in DFIG-based wind energy systems for improved grid stability and efficiency

Wind energy is now a key element in sustainable energy landscape due to growing demand for Renewable Energy Sources (RES). This work presents an enhanced control method for a grid-connected wind energy conversion system (WECS) based doubly-fed induction generator (DFIG) to improve WECS’s efficiency and dependability. The proposed approach is based on a Rider Sea Lion Optimisation (RSLO) algorithm combined with a Recurrent Neural Network (RNN) for Maximum Power Point Tracking (MPPT). This innovative MPPT controller ensures the best possible energy extraction from fluctuating wind speeds. An extra storage device is included to stabilise grid power in order to counteract the erratic and intermittent nature of wind energy. By storing additional wind energy during times of strong wind and distributing it at times of low wind, the system keeps the grid’s electricity supply steady. The proficiency of proposed approach is evaluated in MATLAB/simulation and the outcomes indicate notable gains in grid stability and energy efficiency, demonstrating RSLO–RNN-based MPPT controller’s performance in improving DFIG-based WECS with higher tracking accuracy of (98.92%), THD (0.09%) and ripples compared to other deployed models recently.