Estimation of global solar radiation using artificial neural networks in Abu Dhabi city, United Arab Emirates

Maitha Al-Shamisi, Ali Assi, Hassan Hejase

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)

Abstract

The geographical location (Latitude: 24 deg 28′ N and Longitude: 54 deg 22′ E) of Abu Dhabi city in the United Arab Emirates (UAE) favors the development and utilization of solar energy. This paper presents an artificial neural network (ANN) approach for the estimation of monthly mean global solar radiation (GSR) on a horizontal surface in Abu Dhabi. The ANN models are presented and implemented on a 16-yr measured meteorological data set for Abu Dhabi comprising the maximum daily temperature, mean daily wind speed, mean daily sunshine hours, and mean daily relative humidity between 1993 and 2008. The meteorological data between 1993 and 2003 are used for training the ANN and data between 2004 and 2008 are used for testing the estimated values. Multilayer perceptron (MLP) and radial basis function (RBF) are used as ANN learning algorithms. The results attest to the capability of ANN techniques and their ability to produce accurate estimation models.

Original languageEnglish
Article number024502
JournalJournal of Solar Energy Engineering, Transactions of the ASME
Volume136
Issue number2
DOIs
Publication statusPublished - May 1 2014

Keywords

  • Artificial neural networks
  • Estimation
  • Global solar radiation
  • Mean bias error
  • Modeling
  • Multilayer perceptron
  • Radial basis function
  • Root mean square error

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'Estimation of global solar radiation using artificial neural networks in Abu Dhabi city, United Arab Emirates'. Together they form a unique fingerprint.

Cite this