Solar radiation estimation using aritificial neural networks

Atsu S.S. Dorvlo, Joseph A. Jervase, Ali Al-Lawati

Research output: Contribution to journalArticle

184 Citations (Scopus)

Abstract

Artificial Neural Network Methods are discussed for estimating solar radiation by first estimating the clearness index. Radial Basis Functions, RBF, and Multilayer Perceptron, MLP, models have been investigated using long-term data from eight stations in Oman. It is shown that both the RBF and MLP models performed well based on the root-mean-square error between the observed and estimated solar radiations. However, the RBF models are preferred since they require less computing power. The RBF model, obtained by training with data from the meteorological stations at Masirah, Salalah, Seeb, Sur, Fahud and Sohar, and testing with those from Buraimi and Marmul, was the best. This model can be used to estimate the solar radiation at any location in Oman.

Original languageEnglish
Pages (from-to)307-319
Number of pages13
JournalApplied Energy
Volume71
Issue number4
DOIs
Publication statusPublished - 2002

Fingerprint

Solar radiation
solar radiation
Neural networks
Multilayer neural networks
Mean square error
artificial neural network
Testing
station

Keywords

  • Artificial neural networks
  • Clearness index
  • Radial basis functions
  • Solar radiation

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Energy(all)

Cite this

Solar radiation estimation using aritificial neural networks. / Dorvlo, Atsu S.S.; Jervase, Joseph A.; Al-Lawati, Ali.

In: Applied Energy, Vol. 71, No. 4, 2002, p. 307-319.

Research output: Contribution to journalArticle

Dorvlo, Atsu S.S. ; Jervase, Joseph A. ; Al-Lawati, Ali. / Solar radiation estimation using aritificial neural networks. In: Applied Energy. 2002 ; Vol. 71, No. 4. pp. 307-319.
@article{932637a190734818b4964cdb525856da,
title = "Solar radiation estimation using aritificial neural networks",
abstract = "Artificial Neural Network Methods are discussed for estimating solar radiation by first estimating the clearness index. Radial Basis Functions, RBF, and Multilayer Perceptron, MLP, models have been investigated using long-term data from eight stations in Oman. It is shown that both the RBF and MLP models performed well based on the root-mean-square error between the observed and estimated solar radiations. However, the RBF models are preferred since they require less computing power. The RBF model, obtained by training with data from the meteorological stations at Masirah, Salalah, Seeb, Sur, Fahud and Sohar, and testing with those from Buraimi and Marmul, was the best. This model can be used to estimate the solar radiation at any location in Oman.",
keywords = "Artificial neural networks, Clearness index, Radial basis functions, Solar radiation",
author = "Dorvlo, {Atsu S.S.} and Jervase, {Joseph A.} and Ali Al-Lawati",
year = "2002",
doi = "10.1016/S0306-2619(02)00016-8",
language = "English",
volume = "71",
pages = "307--319",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Elsevier BV",
number = "4",

}

TY - JOUR

T1 - Solar radiation estimation using aritificial neural networks

AU - Dorvlo, Atsu S.S.

AU - Jervase, Joseph A.

AU - Al-Lawati, Ali

PY - 2002

Y1 - 2002

N2 - Artificial Neural Network Methods are discussed for estimating solar radiation by first estimating the clearness index. Radial Basis Functions, RBF, and Multilayer Perceptron, MLP, models have been investigated using long-term data from eight stations in Oman. It is shown that both the RBF and MLP models performed well based on the root-mean-square error between the observed and estimated solar radiations. However, the RBF models are preferred since they require less computing power. The RBF model, obtained by training with data from the meteorological stations at Masirah, Salalah, Seeb, Sur, Fahud and Sohar, and testing with those from Buraimi and Marmul, was the best. This model can be used to estimate the solar radiation at any location in Oman.

AB - Artificial Neural Network Methods are discussed for estimating solar radiation by first estimating the clearness index. Radial Basis Functions, RBF, and Multilayer Perceptron, MLP, models have been investigated using long-term data from eight stations in Oman. It is shown that both the RBF and MLP models performed well based on the root-mean-square error between the observed and estimated solar radiations. However, the RBF models are preferred since they require less computing power. The RBF model, obtained by training with data from the meteorological stations at Masirah, Salalah, Seeb, Sur, Fahud and Sohar, and testing with those from Buraimi and Marmul, was the best. This model can be used to estimate the solar radiation at any location in Oman.

KW - Artificial neural networks

KW - Clearness index

KW - Radial basis functions

KW - Solar radiation

UR - http://www.scopus.com/inward/record.url?scp=0036525799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036525799&partnerID=8YFLogxK

U2 - 10.1016/S0306-2619(02)00016-8

DO - 10.1016/S0306-2619(02)00016-8

M3 - Article

VL - 71

SP - 307

EP - 319

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

IS - 4

ER -