Potential of radial basis function based support vector regression for global solar radiation prediction

Among the different forms of clean energies, solar energy has attracted a lot of attention because it is not only sustainable, but also is renewable and this means that we will never run out of it but the potential of using this form of renewable energy depends on its accessibility. Due to the fact that the number of meteorological stations where global solar radiation (GSR) is recorded, is limited in Iran we were meant to develop four distinctive models based on artificial intelligence in order to prognosticate GSR in Tehran province, Iran. Accordingly, the polynomial and radial basis function (RBF) are applied as the kernel function of Support Vector Regression (SVR) and input energies from different meteorological data obtained from the only station in the studied region were selected as the inputs of the model and the GSR was chosen as the output of the models. Instead of minimizing the observed training error, SVR_poly and SVR_rbf attempt to minimize the generalization error bound so as to achieve generalized performance. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the proposed approach. The calculated root mean square error and correlation coefficient disclosed that SVR_ rbf performed well in predicting GSR. Comparing SVR_rbf results with SVR_poly, ANFIS, and ANN reveals that SVR_rbf outperforms the POLY model in terms of prediction accuracy.