New temperature-based predicting model for global solar radiation using support vector regression

Mawloud Guermoui, Abdelaziz Rabehi, Kacem Gairaa, Saïd Benkaciali

International Journal of Ambient Energy · 2019 · 53 citations · 39 references

Concepts

Abstract

This paper proposes a new approach for daily horizontal global solar radiation prediction using only air temperature as an input. The proposed approach is based on the support vector machine (SVM) by fusing the outcomes of two SVM models. The first one is used to estimate the horizontal global solar radiation, whereas the second one is used to estimate the error produced by the first model. Finally, a weighted sum is applied to predict the global solar radiation. The proposed approach (Corrected-SVM) has been evaluated for Ghardaïa site (Algeria) which is characterised by semi-arid climate conditions, using the measurement of three years (2013–2015). It was found that the proposed Corrected-SVM model improves the performance of the conventional SVM-model. The obtained statistical parameters (mean absolute bias error (MABE), root mean square error (RMSE), relative square error and correlation coefficient (r)) of the C-SVM and conventional SVM model are 1.623, 2.286 MJ/m2, 11.35, 94.20% and 1.713, 2.575 MJ/m2, 12.61, and 93.06%, respectively.

References

39