Show simple record

dc.contributor.authorAhmad, Aziz
dc.contributor.authorAnderson, T.N.
dc.date.accessioned2016-02-20T20:44:36Z
dc.date.available2016-02-20T20:44:36Z
dc.date.issued2014-05
dc.identifier.urihttps://hdl.handle.net/10652/3190
dc.description.abstractIn this study, nonlinear autoregressive recurrent neural networks with exogenous input (NARX) were used to predict global solar radiation across New Zealand. Data for nine hourly weather variables recorded across New Zealand from January 2006 to December 2012 were used to create, train and test Artificial Neural Network (ANN) models using the Levenberg−Marquardt (LM) training algorithm, with global solar radiation as the objective function. In doing this, ANN models with different numbers of neurons (from 5 to 250) in the hidden layer as well as different numbers of delays were experimented with, and their effect on prediction accuracy was analyzed. Subsequently the most accurate ANN model was used for global solar radiation prediction in ten cities across New Zealand. The predicted values of hourly global solar radiation were compared with the measured values, and it was found that the mean squared error (MSE) and regression (R) values showed close correlation. As such, the study illustrates the capability of the model to forecast radiation values at a later time. These results demonstrate the generalization capability of this approach over unseen data and its ability to produce accurate estimates and forecasts.en_NZ
dc.language.isoenen_NZ
dc.publisherSolar 2014 Conference & Expoen_NZ
dc.relation.urihttp://solar.org.au/en_NZ
dc.subjectsolar radiationen_NZ
dc.subjectLevenberg-Marquardten_NZ
dc.subjectneural networksen_NZ
dc.subjectNew Zealanden_NZ
dc.titleGlobal solar radiation prediction using artificial neural network models for New Zealanden_NZ
dc.typeConference Contribution - Oral Presentationen_NZ
dc.rights.holderAuthorsen_NZ
dc.subject.marsden080110 Simulation and Modellingen_NZ
dc.subject.marsden04 Earth Sciencesen_NZ
dc.identifier.bibliographicCitationAhmad, A., and Anderson , T. (2014) Global solar radiation prediction using artificial neural network models for New Zealand. Paper presented at proceedings of the 52nd Annual Australian Solar Council Scientific Conference, Melbourne, May 2014.en_NZ
unitec.institutionUnitec Institute of Technologyen_NZ
unitec.institutionAuckland University of Technologyen_NZ
unitec.publication.spage1en_NZ
unitec.publication.lpage7en_NZ
unitec.conference.title: The 52nd Annual Conference of the Australian Solar Councilen_NZ
unitec.conference.orgAustralian Solar Councilen_NZ
unitec.conference.locationMelbourne Convention & Exhibition Centre, Melbourne, Victoriaen_NZ
unitec.conference.sdate2014-05-08
unitec.conference.edate2014-05-09
unitec.peerreviewedyesen_NZ
dc.contributor.affiliationAuckland University of Technologyen_NZ
unitec.identifier.roms56181en_NZ
unitec.institution.studyareaComputing


Files in this item

Thumbnail

This item appears in

Show simple record


© Unitec Institute of Technology, Private Bag 92025, Victoria Street West, Auckland 1142