Intelligent Predictive Control for Enhancing the Efficiency and Grid Integration of Wind Energy Systems

This research presents a neural network (NN)-based predictive control strategy to enhance the efficiency and sustainability of a wind generator integrated into an electric power system. Focusing on the wind turbine’s grid connection, this approach ensures stability and minimizes voltage fluctuations. Using a permanent magnet synchronous generator (PMSG) model, the NN predictive control is applied to the boost converter and DC/AC inverter, maintaining a stable voltage output despite wind speed variations, thereby optimizing wind energy use. Compared with traditional Proportional-Integral (PI) control, the NN approach achieves similar voltage performance without requiring an additional DC source, offering greater adaptability, robustness, and sustainability under variable conditions. Simulations in Simulink-Matlab demonstrate the NN controller’s effectiveness in stabilizing voltage output and improving grid integration of wind energy. This study underscores the potential of NN-based predictive control in supporting efficient and sustainable renewable energy systems. This research aligns with SDG 7, 9, 11, and 13.