ICNCRE 2013

International Conference on Nanoelectronics, Communications and Renewable Energy 2013

 


ICNCRE 2013 Kokula Krishna Hari K
Short Title ICNCRE 2013
Publisher ASDF, India
ISBN 13 978-81-925233-8-5
ISBN 10 81-925233-8-1
Language English
Type Hard Bound - Printed Book
Copyrights admin@asdf.res.in
Editor-in-Chief Mohamed Rachid Mekideche
Conference Dates 22 - 23, September 2013
Venue Country Jijel, Algeria
Submitted Papers 477
Acceptance Rate 21.17%
Website www.asdf.org.in

Paper 090


Artificial Neural Network Estimation of 5-Min Solar Global Radiation Values Using Air Temperature, Relative Humidity and Wind Speed in The Region of Blida (Algeria)

Artificial Neural Network Estimation of 5-Min Solar Global Radiation Values Using Air Temperature, Relative Humidity and Wind Speed in The Region of Blida (Algeria)

Laidi Maamar1, Cheggaga Nawal2, Hanini Salah3, Ahmed razrazi4, Omar Nadjemi5, Abdallah el Hadj Abdallah6

Saad Dahlab University of Blida, Road of Soumaa
LBMPT, Dr. Yahia Fares University of Medea.

Abstract

Solar energy estimation procedures are very important in the renewable energy field for development of mathematical models, optimization, and advanced control of processes. Solar radiation data provide information on how much of the sun's energy strikes a surface at a location on earth during a particular time period. These data are needed for effective research into solar-energy utilization. Due to the cost and difficulty in measurement, these data are not readily available. Therefore, there is the need to develop alternative ways for generating these data. In this study, an artificial neural network (ANN) was used for the estimation of daily global solar radiation (5-min R-G) on tilted surface using data measured from the meteorological station located inside the University of Blida. Six input parameters were used to train the network. These parameters were elevation, longitude, latitude, air temperature, relative humidity, and wind speed. The optimized network obtained with lowest deviation during the training was one with 6 neurons in the input layer; neurons in the hidden were obtained by trial and error, and one neuron in the output layer. The results show that the ANN can be accurately trained and that the chosen architecture can estimate the 5-min R-G with acceptable accuracy: mean absolute error (MAE) less than 20% for both training and validation step. The low deviations found with the proposed method indicate that it can estimate R-G with better accuracy than other methods available in the literature.

Author's Profile

Laidi Maamar : Profile

Cheggaga Nawal : Profile

Hanini Salah : Profile

Ahmed razrazi : Profile

Omar Nadjemi : Profile

Abdallah el Hadj Abdallah : Profile

Cite this Article as Follows

Laidi Maamar, Cheggaga Nawal, Hanini Salah, Ahmed razrazi, Omar Nadjemi and Abdallah el Hadj Abdallah.Proceedings of The International Conference on Nanoelectronics, Communications and Renewable Energy 2013. Artificial Neural Network Estimation of 5-Min Solar Global Radiation Values Using Air Temperature, Relative Humidity and Wind Speed in The Region of Blida (Algeria). Vol. 1. Chennai: Association of Scientists, Developers and Faculties, 2013. 449-455. Print.