Authors: Shahaboddin Shamshirband Kasra Mohammadi Chong Wen Tong Mazdak Zamani Shervin Motamedi Sudheer Ch
Publish Date: 2015/05/10
Volume: 125, Issue: 1-2, Pages: 53-65
Abstract
In this study a hybrid support vector machine–firefly optimization algorithm SVMFFA model is proposed to estimate monthly mean horizontal global solar radiation HGSR The merit of SVMFFA is assessed statistically by comparing its performance with three previously used approaches Using each approach and longterm measured HGSR three models are calibrated by considering different sets of meteorological parameters measured for Bandar Abbass situated in Iran It is found that the model 3 utilizing the combination of relative sunshine duration difference between maximum and minimum temperatures relative humidity water vapor pressure average temperature and extraterrestrial solar radiation shows superior performance based upon all approaches Moreover the extraterrestrial radiation is introduced as a significant parameter to accurately estimate the global solar radiation The survey results reveal that the developed SVMFFA approach is greatly capable to provide favorable predictions with significantly higher precision than other examined techniques For the SVMFFA 3 the statistical indicators of mean absolute percentage error MAPE root mean square error RMSE relative root mean square error RRMSE and coefficient of determination R 2 are 33252 01859 kWh/m2 37350 and 09737 respectively which according to the RRMSE has an excellent performance As a more evaluation of SVMFFA 3 the ratio of estimated to measured values is computed and found that 47 out of 48 months considered as testing data fall between 090 and 110 Also by performing a further verification it is concluded that SVMFFA 3 offers absolute superiority over the empirical models using relatively similar input parameters In a nutshell the hybrid SVMFFA approach would be considered highly efficient to estimate the HGSRThe authors would like to thank the University of Malaya for the research grants allocated for this project ie the University of Malaya Research Grant RP015C13AET Special appreciation is also credited to the Malaysian Ministry of Education MOE for the Fundamental Research Grant Scheme FP0532013B
Keywords: