Modeling Environmental Parameters Affecting the Performance of Solar Photovoltaic Systems Using Machine Learning

This article explores the application of machine learning models in the analysis of environmental parameters influencing the performance of photovoltaic solar systems. Environmental factors, such as irradiance, temperature, dust, humidity, wind speed, and precipitation, have both direct and indirect effects on the efficiency of PV systems. Machine learning models, including artificial neural networks, regression models, support vector machines, and gradient boosting, have been widely used to predict and optimize PV system performance under varying environmental conditions. The review categorizes studies based on environmental parameters and ML methods, highlighting the strengths and applications of each approach. Key findings indicated that ML models, particularly ANN, and gradient boosting, offer high prediction accuracy and flexibility, enabling more efficient PV system design and operation.