Adaptive co-optimization of artificial neural networks using evolutionary algorithm for global radiation forecasting

Basit Öğe Kaydı
dc.authoridKilic, Fatih/0000-0002-8550-1562
dc.authoridYilmaz, Ibrahim Halil/0000-0001-7840-9162
dc.contributor.authorKılıç, Fatih
dc.contributor.authorYilmaz, Ibrhim Halil
dc.contributor.authorKaya, Ozge
dc.date.accessioned2025-01-06T17:38:10Z
dc.date.available2025-01-06T17:38:10Z
dc.date.issued2021
dc.description.abstractGlobal radiation is not a regularly measured parameter in any weather station relative to other mete-orological parameters due to measurement costs. This study has proposed hybrid artificial neural network models that predicted monthly radiation using typical weather and geographic data. Two datasets and six artificial neural network models were respectively built for indigenous and widespread regions around the world. The referred models co-optimized the artificial neural network properties and feature selection. For this purpose, an adaptive evolutionary algorithm improving prediction perfor-mance was developed to train the neural networks. This novel approach has yielded promising results compared to the developed deep learning models in this study. The results revealed that while the indigenous models had common features of longitude, sunshine durations, precipitation, and wind speed, the widespread models involved those of latitude, sunshine durations, and mean daily maximum air temperature. The proposed hybrid model had respectively the best mean absolute percentage errors of 2.45% and 9.93% for validation dataset and 3.75% and 11.03% for testing dataset of the indigenous and widespread regions, respectively. The present findings showed that the proposed hybrid model could be evaluated as a generic model and could improve the forecasting accuracy with the specified optimization parameters. (c) 2021 Elsevier Ltd. All rights reserved.
dc.description.sponsorshipScientific Project Unit of Adana Alparslan Turkes Science and Technology University [18103034]
dc.description.sponsorshipAuthors acknowledge the financial support received from the Scientific Project Unit of Adana Alparslan Turkes Science and Technology University under Grant no. 18103034.
dc.identifier.doi10.1016/j.renene.2021.02.074
dc.identifier.endpage190
dc.identifier.issn0960-1481
dc.identifier.issn1879-0682
dc.identifier.scopus2-s2.0-85101629721
dc.identifier.scopusqualityQ1
dc.identifier.startpage176
dc.identifier.urihttps://doi.org/10.1016/j.renene.2021.02.074
dc.identifier.urihttps://hdl.handle.net/20.500.14669/2505
dc.identifier.volume171
dc.identifier.wosWOS:000637515800018
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherPergamon-Elsevier Science Ltd
dc.relation.ispartofRenewable Energy
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241211
dc.subjectGlobal radiation
dc.subjectArtificial neural network
dc.subjectHybrid model
dc.subjectEvolutionary algorithm
dc.subjectAdaptive optimization
dc.titleAdaptive co-optimization of artificial neural networks using evolutionary algorithm for global radiation forecasting
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu