Solar Energy Prediction in Algeria: A Supervised Machine Learning Approach

This research investigates the influence of climatic variables on photovoltaic (PV) module performance using supervised machine learning techniques. The dataset was obtained from the Photovoltaic Geographical Information System (PVGIS) and focuses on Tamanrasset, Algeria. MATLAB was used for model development and evaluation. Different machine learning models were compared using R-squared, root mean squared error (RMSE), and mean absolute error (MAE). The neural network models showed the best predictive performance, with R-squared values close to 1 and RMSE values of 3 or lower. The results demonstrate the potential of supervised machine learning for predicting photovoltaic energy production and supporting PV system design under changing climatic conditions.