Modeling the global solar radiation on the earth's surface using atmospheric deterministic and intelligent data-driven techniques

Three methods for analyzing and modeling the global shortwave radiation rea ching the earth's surface are presented in this study. Solar radiation is a very important input for many aspects of climatology, hydrology, atmospher ic sciences, and energy applications. The estimation methods consist of an atmospheric deterministic model and two data-driven intelligent methods. The deterministic method is a broadband atmospheric model, developed for pr edicting the global and diffuse solar radiation incident on the earth's sur face. The intelligent data-driven methods are a new neural network approach in which the hourly values of global radiation for several years are calcu lated and a new fuzzy logic method based on fuzzy sets theory. The two data -driven models, calculating the global solar radiation on a horizontal surf ace, are based on measured data of several meteorological parameters such a s the air temperature, the relative humidity, and the sunshine duration. The three methods are tested and compared using various sets of solar radia tion measurements. The comparison of the three methods showed that the prop osed intelligent techniques can be successfully used for the estimation of global solar radiation during the warm period of the year, while during the cold period the atmospheric deterministic model gives better estimations.