Abstract
Building reliable solar energy systems regardless of whether the system is a photovoltaic or thermal solar energy system requires information about global solar irradiation (sum of direct and diffuse solar radiation projected on a plane (Wh m−2)) in the region where the system is sited. This can be achieved using various solar irradiation estimation techniques particularly for locations where there are no metrological station. Various studies have shown that artificial neural network techniques predict solar irradiation more accurately than conventional methods.
