Title: Artificial neural networks based prediction of hourly horizontal solar radiation data: case study

Authors: Chaba-Mouna Siham; Hanini Salah; Laidi Maamar; Khaouane Latifa

Addresses: Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Algeria ' Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Algeria ' Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Algeria ' Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, Algeria

Abstract: The aim of the present study is to predict global solar radiation (GSR) received on the horizontal surface using artificial neural network (ANN). The measured data of the year (2013) was provided by the Applied Research Unit of Ghardaia - Algeria. The best results were obtained with a 7/24/1 ANN model trained with the quasi-Newton back propagation (BFGS) algorithm. The prediction accuracy for the internal and the external validation set was estimated by the Q²_LOO and Q²_ext which are equal to 0.9984, 0.9977 for ANN, with percent root mean square error (PRMSE) of 4.71% and the mean bias error (MBE) 0.021% for the internal validation and 5.60%, 0.42% for the external validation, respectively. These results show that the optimised model is robust and have a good predictive power explained by a good agreement between the measurement and prediction values of the solar radiation.

Keywords: artificial neural network; ANN; the quasi-Newton back propagation; BFGS; global solar radiation; GSR; prediction; sensitivity analysis.

DOI: 10.1504/IJADS.2017.084312

International Journal of Applied Decision Sciences, 2017 Vol.10 No.2, pp.156 - 174

Received: 26 Sep 2016
Accepted: 03 Feb 2017
Published online: 26 May 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article