Abstract

The effective management of renewable energy facilities, particularly those utilizing solar PV and wind technologies, faces a number of challenges such as weather variability, data resolution, and handling large data volumes. The number of publications addressing these issues is increasing, and it is anticipated that this growth will continue in the near term. Implementing data analysis tools for power plant management can enhance our understanding of weather events and improve electric power generation forecasting accuracy. Despite common characteristics between solar PV and wind energy, including their reliance on weather conditions, handling data volumes, and processing time series data, few studies offer a comprehensive view of generalizing forecast models. Our objective is to determine the trends in forecasts models in this area, the most commonly used techniques that show better performance and efficiency, the variables involved in each type of energy, among other aspects. A systematic mapping study of scientific literature was performed, selecting 75 primary studies grouped by type of machine learning technique. Some common aspects were found regardless of the type of energy, solar PV or wind, mainly related to single or hybrid forecasting models. Other common factors found are the types of model optimization algorithms used and feature extraction and decomposition techniques. The study highlights the importance of hybrid models that demonstrate, compared to conventional or individual models, significant improvements in the level of accuracy of their forecasts for both solar PV and wind energy, combining various statistical, machine learning or deep learning techniques.