DATA-DRIVEN WIND TURBINE PERFORMANCE ASSESSMENT USING MACHINE LEARNING IN DYNAMIC CLIMATIC CONDITIONS

Abstract

The rapid expansion of wind energy has increased the need for accurate and intelligent methods to evaluate wind turbine performance under varying environmental conditions. Traditional performance assessment techniques often struggle to capture the complex and nonlinear relationships between climatic factors and turbine output. This study presents a data-driven framework for wind turbine performance assessment using machine learning techniques in dynamic climatic conditions. The proposed approach utilizes historical operational data, including wind speed, wind direction, temperature, humidity, atmospheric pressure, and turbine power output, to develop predictive models capable of identifying performance variations and operational inefficiencies. Advanced machine learning algorithms such as Random Forest, Support Vector Machine, and Gradient Boosting are employed to analyze largescale datasets and estimate turbine performance with high accuracy. Feature engineering and data preprocessing techniques are applied to improve model robustness and reliability. The developed models are evaluated using standard performance metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R²). Experimental results demonstrate that machine learning-based assessment significantly enhances prediction accuracy and enables early detection of performance degradation caused by changing climatic conditions. The findings highlight the potential of intelligent data analytics in improving operational efficiency, reducing maintenance costs, and supporting sustainable wind energy generation. The proposed framework offers a scalable and practical solution for real-time monitoring and performance optimization of modern wind turbine systems operating in diverse environmental conditions.