Prediction of daily global solar radiation using different machine learning algorithms: Evaluation and comparison

Basit Öğe Kaydı
dc.authoridAgbulut, Umit/0000-0002-6635-6494
dc.contributor.authorAgbulut, Umit
dc.contributor.authorGurel, Ali Etem
dc.contributor.authorBicen, Yunus
dc.date.accessioned2021-12-01T18:46:59Z
dc.date.available2021-12-01T18:46:59Z
dc.date.issued2021
dc.department[Belirlenecek]en_US
dc.description.abstractThe prediction of global solar radiation for the regions is of great importance in terms of giving directions of solar energy conversion systems (design, modeling, and operation), selection of proper regions, and even future investment policies of the decision-makers. With this viewpoint, the objective of this paper is to predict daily global solar radiation data of four provinces (Kirklareli, Tokat, Nevsehir and Karaman) which have different solar radiation distribution in Turkey. In the study, four different machine learning algorithms (support vector machine (SVM), artificial neural network (ANN), kernel and nearest-neighbor (k-NN), and deep learning (DL)) are used. In the training of these algorithms, daily minimum and maximum ambient temperature, cloud cover, daily extraterrestrial solar radiation, day length and solar radiation of these provinces are used. The data is supplied from the Turkish State Meteorological Service and cover the last two years (01.01.2018-31.12.2019). To decide on the success of these algorithms, seven different statistical metrics (R-2, RMSE, rRMSE, MBE, MABE, t-stat, and MAPE) are discussed in the study. The results shows that R2, MABE, and RMSE values of all algorithms are ranging from 0.855 to 0.936, from 1.870 to 2.328 MJ/m(2), from 2.273 to 2.820 MJ/m(2), respectively. At all cases, k-NN exhibited the worst result in terms of R-2, RMSE, and MABE metrics. Of all the models, DL was the only model that exceeded the t-critic value. In conclusion, the present paper is reporting that all machine learning algorithms tested in this study can be used in the prediction of daily global solar radiation data with a high accuracy; however, the ANN algorithm is the best fitting algorithm among all algorithms. Then it is followed by DL, SVM and k-NN, respectively.en_US
dc.description.sponsorshipDuzce University Scientific Research Projects Coordination UnitDuzce University [2019.07.04.1049.2019.07.04.1049]en_US
dc.description.sponsorshipThis work is supported by Duzce University Scientific Research Projects Coordination Unit. Project Number: 2019.07.04.1049.2019.07.04.1049.en_US
dc.identifier.doi10.1016/j.rser.2020.110114
dc.identifier.issn1364-0321
dc.identifier.issn1879-0690
dc.identifier.scopus2-s2.0-85089465236en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1016/j.rser.2020.110114
dc.identifier.urihttps://hdl.handle.net/20.500.12684/10087
dc.identifier.volume135en_US
dc.identifier.wosWOS:000592370700001en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherPergamon-Elsevier Science Ltden_US
dc.relation.ispartofRenewable & Sustainable Energy Reviewsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDaily global solar radiationen_US
dc.subjectMachine learning algorithmsen_US
dc.subjectSolar energyen_US
dc.subjectPredictionen_US
dc.subjectModel comparisonen_US
dc.subjectSupport Vector Machineen_US
dc.subjectArtificial-Intelligence Methodsen_US
dc.subjectEmpirical-Modelsen_US
dc.subjectNeural-Networksen_US
dc.subjectAnnen_US
dc.subjectRegressionen_US
dc.subjectParametersen_US
dc.subjectSelectionen_US
dc.subjectTemperaturesen_US
dc.subjectIrradiationen_US
dc.titlePrediction of daily global solar radiation using different machine learning algorithms: Evaluation and comparisonen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
10087.pdf
Boyut:
1.34 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu