The Prediction of Solar Radiation for Five Meteorological Stations in Libya Using Adaptive Neuro-Fuzzy Inference System (ANFIS)

Abstract

The prediction of solar radiation is a very important tool in climatology, hydrology, and energy applications, as it permits estimating solar data for locations where measurements are not available. In this paper, an adaptive neuro-fuzzy inference system -ANFIS- is presented to predict the monthly global solar radiation on a horizontal surface in Libya. The real meteorological solar radiation data from 5 stations for the period of 1982 - 2009 with different latitudes and longitudes were used in the current study. The data set is divided into two subsets; the first is used for training and the latter is used for testing the model. -ANFIS- combines fuzzy logic and neural network techniques that are used in order to gain more efficiency. The statistical performance parameters such as root mean square error (RMSE), mean absolute percentage error(MAPE) and the coefficient of efficiency (E) was calculated to check the adequacy of the model. On the basis of coefficient of efficiency, as well as the scatter diagrams and the error modes, the predicted results indicate that the neuro-fuzzy model gives reasonable results: accuracy of about 92% - 96% and the RMSE ranges between 0.22 - 0.35 kW.hr/m2/day