Daily global solar radiation prediction from air temperatures using kernel extreme learning machine: a case study for Iran

Abstract

Lately, the kernel extreme learning machine (KELM) has gained considerable importance in the scientific area due to its great efficiency, easy implementation and fast training speed. In this paper, for the first time the potential of KELM to predict the daily horizontal global solar radiation from the maximum and minimum air temperatures (Tmax and Tmin) is appraised. The effectiveness of the proposed KELM method is evaluated against the grid search based support vector regression (SVR), as a robust methodology. Three KELM and SVR models are developed using different input attributes including: (1) Tmin and Tmax, (2) Tmin and Tmax−Tmin, and (3) Tmax and Tmax−Tmin. The achieved results reveal that the best predictions precision is achieved by models (3). The achieved results demonstrate that KELM offers favorable predictions and outperforms the SVR. For the KELM (3) model, the obtained statistical parameters of mean absolute bias error, root mean square error, relative root mean square error and correlation coefficient are 1.3445 MJ/m2, 2.0164 MJ/m2, 11.2464% and 0.9057%, respectively for the testing data. As further examination, a month-by-month evaluation is conducted and found that in six months from May to October the KELM (3) model provides further accuracy than overall accuracy. Based upon the relative root mean square error, the KELM (3) model shows excellent capability in the period of April to October while in the remaining months represents good performance.