Development of a Model to Predict the Global Solar Radiation Using Statistical Techniques

An precise information of solar radiation distribution at a actual geographical place is of vital importance for the advance of many solar energy devices. In this study, global solar radiation received on horizontal surfaces and sunshine duration for the city of Bandar Seri Iskandar, Tronoh Perak northern region of west coast peninsular Malaysia was analyzed. For areas where no real measured values are obtainable, a common exercise is to estimate mean daily global solar radiation using appropriate empirical correlations based on the measured relevant information at those sites. In this study, three sunshine-based models which is first, second and third order polynomial was used to develop the new model. In order to assess for the performance and validation, statistical significance of the models which is mean bias error (MBE), root mean square error (RMSE), mean percentage error (MPE) and mean bias error (MABE) were conducted to determine the accuracy and precise of the models. This research involves in a comprehensive statistical investigation and directly related to engineering scope.