Estimation of 5-min time-step data of tilted solar global irradiation using ANN (Artificial Neural Network) model


Dahmani K., Dizene R., Notton G., Paoli C., Voyant C., Nivet M. L.

ENERGY, vol.70, pp.374-381, 2014 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 70
  • Publication Date: 2014
  • Doi Number: 10.1016/j.energy.2014.04.011
  • Journal Name: ENERGY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.374-381
  • Galatasaray University Affiliated: Yes

Abstract

Converting measured horizontal global solar irradiance in tilted ones is a difficult task, particularly for a small time-step and for not-averaged data. Conventional methods (statistical, correlation, ...) are not always efficient with time-step less than one hour; thus, we want to know if an ANN (Artificial Neural Network) is able to realize this conversion with a good accuracy when applied to 5-min solar radiation data of Bouzareah, Algeria. The ANN is developed and optimized using two years of solar data; the nRMSE (relative root means square error) is around 8% for the optimal configuration, which corresponds to a very good accuracy for such a short time-step. (C) 2014 Elsevier Ltd. All rights reserved.