Learning Processes to Predict the Hourly Global, Direct, and Diffuse Solar Irradiance from Daily Global Radiation with Artificial Neural Networks

Abstract

This paper presents three different topologies of feed forward neural network (FFNN) models for generating global, direct, and diffuse hourly solar irradiance in the city of Fez (Morocco). Results from this analysis are crucial for the conception of any solar energy system. Especially, for the concentrating ones, as direct component is seldom measured. For the three models, the main input was the daily global irradiation with other radiometric and meteorological parameters. Three years of hourly data were available for this study. For each solar component's prediction, different combinations of inputs as well as different numbers of hidden neurons were considered. To evaluate these models, the regression coefficient (R2) and normalized root mean square error (nRMSE) were used. The test of these models over unseen data showed a good accuracy and proved their generalization capability (nRMSE = 13.1%, 9.5%, and 8.05% and R = 0.98, 0.98, and 0.99) for hourly global, hourly direct, and daily direct radiation, respectively. Different comparison analyses confirmed that (FFNN) models surpass other methods of estimation. As such, the proposed models showed a good ability to generate different solar components from daily global radiation which is registered in most radiometric stations.