Daily Surface Solar Radiation Prediction Mapping Using Artificial Neural Network: The Case Study of Reunion Island

Abstract

This paper focuses on the prediction of daily surface solar radiation maps for Reunion Island by a hybrid approach that combines principal component analysis (PCA), wavelet transform analysis, and artificial neural network (ANN). The daily surface solar radiation over 18 years (1999–2016) from CM SAF (SARAH-E with 0.05 deg × 0.05 deg spatial resolution) is first detrended using the clear sky index. Dimensionality reduction of the detrended dataset is secondly performed through PCA, which results in saving computational time by a factor of eight in comparison to not using PCA. A wavelet transform is thirdly applied onto each of the first 28 principal components (PCs) explaining 95% of the variance. The decomposed nine-wavelet components for each PC are fourthly used as input to an ANN model to perform the prediction of day-ahead surface solar radiation. The predicted decomposed components are finally returned to PCs and clear sky indices, irradiation in the end for re-mapping the surface solar radiation's distribution. It is found that the prediction accuracy is quite satisfying: root mean square error (RMSE) is 30.98 W/m2 and the (1 − RMSE_prediction/RMSE_persistence) is 0.409.