COMPARATIVE ANALYSIS OF MODELS FOR SOLAR STATION OUTPUT PREDICTION

Abstract

This research paper explores the prediction of solar energy radiation using various machine learning methods and neural networks. The results are presented based on the analysis of four different datasets obtained from solar stations. The study begins with an overview of solar energy in the context of contemporary challenges in the fields of energy and environmental sustainability, and reviews previous research related to the application of artificial intelligence in solar energy. The main contribution of the work lies in the analysis and comparison of diverse machine learning models and neural networks for predicting solar energy radiation. The results are compared considering accuracy metrics (RMSE - Root Mean Squared Error, MAE - Mean Absolute Error, MRE - Mean Relative Error) and execution times for each model. Each model is evaluated on four datasets with different characteristics.