Modeling of solar energy potential in Souss-Massa area-Morocco, using intelligence Artificial Neural Networks (ANNs)

Abstract

Special attention has been focused on the application of Artificial Neural Networks (ANNs) especially in the renewable energy field, particularly for meteorological data prediction such as solar radiation. For this reason, we have developed a model based on Multi-layer perceptron (MLP) to predict the evolution of the global monthly solar irradiation in the Souss-Massa area (south-west of Morocco). In this study, a large database on a wide period (1994-2003) has been used. This database contains a set of metrological and geographical data such as: Latitude, Longitude, months of the year, the average temperature, the sunshine duration, relative humidity and the average of the monthly global solar irradiation. The appropriate model that gives a minimum of Root Mean Square Error (RMSE) has been found after testing numerous models. Furthermore, the almost perfect coefficient of correlation (R) was found, between measured and predicted values.