<![CDATA[The utilization of renewable energy is experiencing significant growth, with wind turbines emerging as a key solution for generating environmentally friendly electricity. However, the efficiency of wind turbines is highly dependent on their operational parameters, such as wind speed, blade size, angular velocity, and torque. This research aims to optimize the operational parameters of small-scale wind turbines using an XGBoost-based Machine Learning model and an L-BFGS-B algorithm-based optimization method. A simulation dataset was generated based on the physical equations of wind turbine power and a MATLAB Simulink model, incorporating added noise to approximate real-world conditions. The XGBoost model was trained to predict the turbine's output power based on its operational parameters. Subsequently, an optimization method was employed to identify the parameter combination that yields maximum power. The experimental results demonstrate that the model exhibits strong performance, characterized by a low Mean Squared Error (MSE) and a high R-squared score. The optimization process successfully achieved a significant increase in power output compared to the initial configuration. Through this approach, wind turbine systems can operate more efficiently and generate optimal electrical power. This study contributes to the advancement of artificial intelligence-based optimization strategies for renewable energy systems.]]>
Copyrights © 2025
