Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia

Tamer Khatib, Azah Mohamed, Marwan Mahmoud, Kamaruzzaman Sopian

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

This paper presents models for global and diffuse solar energy on a horizontal surface for main five sites in Malaysia. The global solar energy is modeled using linear, nonlinear, fuzzy logic, and artificial neural network (ANN) models, while the diffuse solar energy is modeled using linear, nonlinear, and ANN models. Three statistical values are used to evaluate the developed solar energy models, namely, the mean absolute percentage error, MAPE; root mean square error, RMSE; and mean bias error, MBE. The results showed that the ANN models are superior compared with the other models in which the MAPE in calculating the global solar energy in Malaysia by the ANN model is 5.38%, while the MAPE for the linear, nonlinear, and fuzzy logic models are 8.13%, 6.93%, and 6.71%, respectively. The results for the diffuse solar energy showed that the MAPE of the ANN model is 1.53%, while the MAPE of the linear and nonlinear models are 4.35% and 3.74%, respectively. The accurate ANN models can therefore be used to predict solar energy in Malaysia and nearby regions.

Original languageEnglish
Pages (from-to)795-819
Number of pages25
JournalInternational Journal of Green Energy
Volume8
Issue number8
DOIs
Publication statusPublished - 1 Nov 2011

Fingerprint

Solar energy
Neural networks
Fuzzy logic
Molecular beam epitaxy
Mean square error

Keywords

  • ANN
  • Diffuse solar energy
  • Global solar energy
  • Malaysia
  • Solar energy modeling

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

Cite this

Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia. / Khatib, Tamer; Mohamed, Azah; Mahmoud, Marwan; Sopian, Kamaruzzaman.

In: International Journal of Green Energy, Vol. 8, No. 8, 01.11.2011, p. 795-819.

Research output: Contribution to journalArticle

@article{3d4ea0070bf7430d911f6a641537b0d9,
title = "Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia",
abstract = "This paper presents models for global and diffuse solar energy on a horizontal surface for main five sites in Malaysia. The global solar energy is modeled using linear, nonlinear, fuzzy logic, and artificial neural network (ANN) models, while the diffuse solar energy is modeled using linear, nonlinear, and ANN models. Three statistical values are used to evaluate the developed solar energy models, namely, the mean absolute percentage error, MAPE; root mean square error, RMSE; and mean bias error, MBE. The results showed that the ANN models are superior compared with the other models in which the MAPE in calculating the global solar energy in Malaysia by the ANN model is 5.38{\%}, while the MAPE for the linear, nonlinear, and fuzzy logic models are 8.13{\%}, 6.93{\%}, and 6.71{\%}, respectively. The results for the diffuse solar energy showed that the MAPE of the ANN model is 1.53{\%}, while the MAPE of the linear and nonlinear models are 4.35{\%} and 3.74{\%}, respectively. The accurate ANN models can therefore be used to predict solar energy in Malaysia and nearby regions.",
keywords = "ANN, Diffuse solar energy, Global solar energy, Malaysia, Solar energy modeling",
author = "Tamer Khatib and Azah Mohamed and Marwan Mahmoud and Kamaruzzaman Sopian",
year = "2011",
month = "11",
day = "1",
doi = "10.1080/15435075.2011.602156",
language = "English",
volume = "8",
pages = "795--819",
journal = "International Journal of Green Energy",
issn = "1543-5075",
publisher = "Taylor and Francis Ltd.",
number = "8",

}

TY - JOUR

T1 - Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia

AU - Khatib, Tamer

AU - Mohamed, Azah

AU - Mahmoud, Marwan

AU - Sopian, Kamaruzzaman

PY - 2011/11/1

Y1 - 2011/11/1

N2 - This paper presents models for global and diffuse solar energy on a horizontal surface for main five sites in Malaysia. The global solar energy is modeled using linear, nonlinear, fuzzy logic, and artificial neural network (ANN) models, while the diffuse solar energy is modeled using linear, nonlinear, and ANN models. Three statistical values are used to evaluate the developed solar energy models, namely, the mean absolute percentage error, MAPE; root mean square error, RMSE; and mean bias error, MBE. The results showed that the ANN models are superior compared with the other models in which the MAPE in calculating the global solar energy in Malaysia by the ANN model is 5.38%, while the MAPE for the linear, nonlinear, and fuzzy logic models are 8.13%, 6.93%, and 6.71%, respectively. The results for the diffuse solar energy showed that the MAPE of the ANN model is 1.53%, while the MAPE of the linear and nonlinear models are 4.35% and 3.74%, respectively. The accurate ANN models can therefore be used to predict solar energy in Malaysia and nearby regions.

AB - This paper presents models for global and diffuse solar energy on a horizontal surface for main five sites in Malaysia. The global solar energy is modeled using linear, nonlinear, fuzzy logic, and artificial neural network (ANN) models, while the diffuse solar energy is modeled using linear, nonlinear, and ANN models. Three statistical values are used to evaluate the developed solar energy models, namely, the mean absolute percentage error, MAPE; root mean square error, RMSE; and mean bias error, MBE. The results showed that the ANN models are superior compared with the other models in which the MAPE in calculating the global solar energy in Malaysia by the ANN model is 5.38%, while the MAPE for the linear, nonlinear, and fuzzy logic models are 8.13%, 6.93%, and 6.71%, respectively. The results for the diffuse solar energy showed that the MAPE of the ANN model is 1.53%, while the MAPE of the linear and nonlinear models are 4.35% and 3.74%, respectively. The accurate ANN models can therefore be used to predict solar energy in Malaysia and nearby regions.

KW - ANN

KW - Diffuse solar energy

KW - Global solar energy

KW - Malaysia

KW - Solar energy modeling

UR - http://www.scopus.com/inward/record.url?scp=84857838553&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857838553&partnerID=8YFLogxK

U2 - 10.1080/15435075.2011.602156

DO - 10.1080/15435075.2011.602156

M3 - Article

VL - 8

SP - 795

EP - 819

JO - International Journal of Green Energy

JF - International Journal of Green Energy

SN - 1543-5075

IS - 8

ER -