mobile

Under the patronage of:

Journal Metrics


CiteScore: 1.10


More about CiteScore


Source Normalized Impact per Paper (SNIP): 0.574


SCImago Journal Rank (SJR): 0.321

 
SCImago Journal & Country Rank
 

Novel Approach for Estimating Monthly Sunshine Duration Using Artificial Neural Networks: A Case Study

Journal of Sustainable Development of Energy, Water and Environment Systems
Volume 6, Issue 3, pp 405-414
DOI: http://dx.doi.org/10.13044/j.sdewes.d6.0226
Maamar Laidi , Salah Hanini, Abdallah El Hadj Abdallah
Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, BD de L’A.L.N Ain D’heb Médéa, Médéa, Algeria

Abstract

This work deals with the potential application of artificial neural networks to model sunshine duration in three cities in Algeria using ten input parameters. These latter are: year and month, longitude, latitude and altitude of the site, minimum, mean and maximum air temperature, wind speed and relative humidity. They were selected according to their availability in meteorological stations and based on the fact that they are considered as the most used parameters by researchers to model sunshine duration using artificial neural networks. Several network architectures were tested to choose the most accurate and simple scheme. The optimum number of layers and neurons was determined by trial and error method. The optimized network was obtained using Levenberg-Marquardt back-propagation algorithm, one hidden layer including 25 neurons with Tan-sigmoid transfer function. The model developed in this study has the ability to estimate sunshine duration with a mean absolute percentage error value equals to 2.015%, a percentage root mean square error of 2.741% and a determination coefficient of 0.9993 during test stage.

Keywords: Sunshine duration, Solar energy, Artificial neural networks, Root mean square error, Meteorological parameters.

Creative Commons License
Views (in 2018): 215 | Downloads (in 2018): 127
Total views: 215 | Total downloads: 127

DBG