Effectiveness of un-decimated wavelet transform in time-series forecasting: A PV power calculation case study in BTU

Basit Öğe Kaydı
dc.authorid0000-0003-0423-1968
dc.authorid0000-0002-5136-0829
dc.authorid0000-0001-9613-6620
dc.contributor.authorAlbayram, Mehmet
dc.contributor.authorYilmaz, Alper
dc.contributor.authorBayrak, Gokay
dc.contributor.authorBasaran, Kivanc
dc.contributor.authorPopescu, Luminita Georgeta
dc.date.accessioned2026-02-08T15:15:28Z
dc.date.available2026-02-08T15:15:28Z
dc.date.issued2026
dc.departmentBursa Teknik Üniversitesi
dc.description.abstractThis study explored the effectiveness of Un-Decimated Wavelet Transform (UWT) in time-series applications, using photovoltaic (PV) calculation as a case study. Real-time measurements of irradiance, ambient temperature, module temperature, and humidity were collected at 5-min intervals from a 1.2 kW rooftop PV system at Bursa Technical University. Wavelet-based features extracted with both UWT and the conventional Discrete Wavelet Transform (DWT) were combined with regression and tree-based learners to build 16 hybrid models. The results show that the shift-invariant UWT significantly improves both feature extraction and prediction accuracy compared to the DWT approach. The UWT-DT model achieved the highest accuracy, with the lowest MSE (0.0001), the lowest RMSE (0.0118) and the highest R-2 coefficient (0.9986). A Wilcoxon signed-rank test applied to paired RMSE values confirmed that these improvements were statistically significant (p value < 0.05 for UWTDT vs DWT-DT). In terms of computational complexity, the 'a` trous' algorithm used in UWT requires convolution operations at every level, resulting in higher processing costs than DWT (12 ms feature extraction per 1024-sample input). However, the full-resolution features provided by UWT significantly reduced the error rates of treebased models, raising R-2 above 0.99.
dc.description.sponsorshipMinistry of Research, Innovation and Digitalization [PNRR-C9-I8-760089/23.05.2023, CF31/14.11.2022]
dc.description.sponsorshipThis work was supported by a grant of the Ministry of Research, Innovation and Digitalization, project number PNRR-C9-I8-760089/23.05.2023, code CF31/14.11.2022.
dc.identifier.doi10.1016/j.renene.2025.124062
dc.identifier.issn0960-1481
dc.identifier.issn1879-0682
dc.identifier.scopus2-s2.0-105011590709
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.renene.2025.124062
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5778
dc.identifier.volume256
dc.identifier.wosWOS:001543573200001
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.snmzWOS_KA_20260207
dc.subjectUn-decimated wavelet transform
dc.subjectMachine learning
dc.subjectRegression
dc.subjectEnsemble learning
dc.subjectPV power forecasting
dc.titleEffectiveness of un-decimated wavelet transform in time-series forecasting: A PV power calculation case study in BTU
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu