A computation ANN model for quantifying the global solar radiation: A case study of Al-Aqabah-Jordan

I. M. Abolgasem, M. A. Alghoul, Mohd Hafidz Ruslan, Hoy Yen Chan, N. G. Khrit, Kamaruzzaman Sopian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a computation model is developed to predict the global solar radiation (GSR) in Aqaba city based on the data recorded with association of Artificial Neural Networks (ANN). The data used in this work are global solar radiation (GSR), sunshine duration, maximum & minimum air temperature and relative humidity. These data are available from Jordanian meteorological station over a period of two years. The quality of GSR forecasting is compared by using different Learning Algorithms. The decision of changing the ANN architecture is essentially based on the predicted results to obtain the best ANN model for monthly and seasonal GSR. Different configurations patterns were tested using available observed data. It was found that the model using mainly sunshine duration and air temperature as inputs gives accurate results. The ANN model efficiency and the mean square error values show that the prediction model is accurate. It is found that the effect of the three learning algorithms on the accuracy of the prediction model at the training and testing stages for each time scale is mostly within the same accuracy range.

Original languageEnglish
Title of host publicationIOP Conference Series: Materials Science and Engineering
PublisherInstitute of Physics Publishing
Volume88
Edition1
DOIs
Publication statusPublished - 21 Sep 2015
Event7th International Conference on Cooling and Heating Technologies, ICCHT 2014 - Subang Jaya, Selangor Darul Ehsan, Malaysia
Duration: 4 Nov 20146 Nov 2014

Other

Other7th International Conference on Cooling and Heating Technologies, ICCHT 2014
CountryMalaysia
CitySubang Jaya, Selangor Darul Ehsan
Period4/11/146/11/14

Fingerprint

Solar radiation
Neural networks
Learning algorithms
Air
Network architecture
Mean square error
Atmospheric humidity
Temperature
Testing

ASJC Scopus subject areas

  • Engineering(all)
  • Materials Science(all)

Cite this

Abolgasem, I. M., Alghoul, M. A., Ruslan, M. H., Chan, H. Y., Khrit, N. G., & Sopian, K. (2015). A computation ANN model for quantifying the global solar radiation: A case study of Al-Aqabah-Jordan. In IOP Conference Series: Materials Science and Engineering (1 ed., Vol. 88). [012073] Institute of Physics Publishing. https://doi.org/10.1088/1757-899X/88/1/012073

A computation ANN model for quantifying the global solar radiation : A case study of Al-Aqabah-Jordan. / Abolgasem, I. M.; Alghoul, M. A.; Ruslan, Mohd Hafidz; Chan, Hoy Yen; Khrit, N. G.; Sopian, Kamaruzzaman.

IOP Conference Series: Materials Science and Engineering. Vol. 88 1. ed. Institute of Physics Publishing, 2015. 012073.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abolgasem, IM, Alghoul, MA, Ruslan, MH, Chan, HY, Khrit, NG & Sopian, K 2015, A computation ANN model for quantifying the global solar radiation: A case study of Al-Aqabah-Jordan. in IOP Conference Series: Materials Science and Engineering. 1 edn, vol. 88, 012073, Institute of Physics Publishing, 7th International Conference on Cooling and Heating Technologies, ICCHT 2014, Subang Jaya, Selangor Darul Ehsan, Malaysia, 4/11/14. https://doi.org/10.1088/1757-899X/88/1/012073
Abolgasem IM, Alghoul MA, Ruslan MH, Chan HY, Khrit NG, Sopian K. A computation ANN model for quantifying the global solar radiation: A case study of Al-Aqabah-Jordan. In IOP Conference Series: Materials Science and Engineering. 1 ed. Vol. 88. Institute of Physics Publishing. 2015. 012073 https://doi.org/10.1088/1757-899X/88/1/012073
Abolgasem, I. M. ; Alghoul, M. A. ; Ruslan, Mohd Hafidz ; Chan, Hoy Yen ; Khrit, N. G. ; Sopian, Kamaruzzaman. / A computation ANN model for quantifying the global solar radiation : A case study of Al-Aqabah-Jordan. IOP Conference Series: Materials Science and Engineering. Vol. 88 1. ed. Institute of Physics Publishing, 2015.
@inproceedings{1fbe9c1f591a426498ab632d5a07c728,
title = "A computation ANN model for quantifying the global solar radiation: A case study of Al-Aqabah-Jordan",
abstract = "In this paper, a computation model is developed to predict the global solar radiation (GSR) in Aqaba city based on the data recorded with association of Artificial Neural Networks (ANN). The data used in this work are global solar radiation (GSR), sunshine duration, maximum & minimum air temperature and relative humidity. These data are available from Jordanian meteorological station over a period of two years. The quality of GSR forecasting is compared by using different Learning Algorithms. The decision of changing the ANN architecture is essentially based on the predicted results to obtain the best ANN model for monthly and seasonal GSR. Different configurations patterns were tested using available observed data. It was found that the model using mainly sunshine duration and air temperature as inputs gives accurate results. The ANN model efficiency and the mean square error values show that the prediction model is accurate. It is found that the effect of the three learning algorithms on the accuracy of the prediction model at the training and testing stages for each time scale is mostly within the same accuracy range.",
author = "Abolgasem, {I. M.} and Alghoul, {M. A.} and Ruslan, {Mohd Hafidz} and Chan, {Hoy Yen} and Khrit, {N. G.} and Kamaruzzaman Sopian",
year = "2015",
month = "9",
day = "21",
doi = "10.1088/1757-899X/88/1/012073",
language = "English",
volume = "88",
booktitle = "IOP Conference Series: Materials Science and Engineering",
publisher = "Institute of Physics Publishing",
edition = "1",

}

TY - GEN

T1 - A computation ANN model for quantifying the global solar radiation

T2 - A case study of Al-Aqabah-Jordan

AU - Abolgasem, I. M.

AU - Alghoul, M. A.

AU - Ruslan, Mohd Hafidz

AU - Chan, Hoy Yen

AU - Khrit, N. G.

AU - Sopian, Kamaruzzaman

PY - 2015/9/21

Y1 - 2015/9/21

N2 - In this paper, a computation model is developed to predict the global solar radiation (GSR) in Aqaba city based on the data recorded with association of Artificial Neural Networks (ANN). The data used in this work are global solar radiation (GSR), sunshine duration, maximum & minimum air temperature and relative humidity. These data are available from Jordanian meteorological station over a period of two years. The quality of GSR forecasting is compared by using different Learning Algorithms. The decision of changing the ANN architecture is essentially based on the predicted results to obtain the best ANN model for monthly and seasonal GSR. Different configurations patterns were tested using available observed data. It was found that the model using mainly sunshine duration and air temperature as inputs gives accurate results. The ANN model efficiency and the mean square error values show that the prediction model is accurate. It is found that the effect of the three learning algorithms on the accuracy of the prediction model at the training and testing stages for each time scale is mostly within the same accuracy range.

AB - In this paper, a computation model is developed to predict the global solar radiation (GSR) in Aqaba city based on the data recorded with association of Artificial Neural Networks (ANN). The data used in this work are global solar radiation (GSR), sunshine duration, maximum & minimum air temperature and relative humidity. These data are available from Jordanian meteorological station over a period of two years. The quality of GSR forecasting is compared by using different Learning Algorithms. The decision of changing the ANN architecture is essentially based on the predicted results to obtain the best ANN model for monthly and seasonal GSR. Different configurations patterns were tested using available observed data. It was found that the model using mainly sunshine duration and air temperature as inputs gives accurate results. The ANN model efficiency and the mean square error values show that the prediction model is accurate. It is found that the effect of the three learning algorithms on the accuracy of the prediction model at the training and testing stages for each time scale is mostly within the same accuracy range.

UR - http://www.scopus.com/inward/record.url?scp=84948442060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948442060&partnerID=8YFLogxK

U2 - 10.1088/1757-899X/88/1/012073

DO - 10.1088/1757-899X/88/1/012073

M3 - Conference contribution

AN - SCOPUS:84948442060

VL - 88

BT - IOP Conference Series: Materials Science and Engineering

PB - Institute of Physics Publishing

ER -