Generalized feed-forward based method for wind energy prediction

Basit Öğe Kaydı
dc.authorid0000-0001-7547-9413en_US
dc.contributor.authorÇelik, Ali Naci
dc.contributor.authorKolhe, Mohan
dc.date.accessioned2021-06-23T19:35:11Z
dc.date.available2021-06-23T19:35:11Z
dc.date.issued2013
dc.departmentBAİBÜ, Mühendislik Fakültesi, Makine Mühendisliği Bölümüen_US
dc.description.abstractEven though a number of new mathematical functions have been proposed for modeling wind speed probability density distributions, still the Weibull function continues to be the most commonly used model in the literature. Therefore, the parameters of this function are still widely used to obtain typical wind probability density distributions for finding the wind energy potential by researchers, engineers and designers. Once long-term average of Weibull function's parameters are known, then the probability density distributions can easily be obtained. Artificial neural network (ANN) can be used as alternative to analytical approach as ANN offers advantages such as no required knowledge of internal system parameters, compact solution for multi-variable problems. In this work, a generalized feed-forward type of neural network is used to predict an annual wind speed probability density distribution by using the Weibull function's parameters as inputs. For verifying its validity and merits, the annual wind speed probability density distribution is also predicted by using the Weibull function. The wind speed distribution predicted from the ANN modeling is compared with the analytical model's results. Total 9 year long hourly wind speed data, belonging to one of the windiest locations in Turkey with mean wind speed of over 6 m/s, are used in this study. It is observed that ANN based wind speed distribution estimation gives better results for calculating the energy output from some commercial wind turbine generators. (C) 2012 Elsevier Ltd. All rights reserved.en_US
dc.identifier.doi10.1016/j.apenergy.2012.06.040
dc.identifier.endpage588en_US
dc.identifier.issn0306-2619
dc.identifier.issn1872-9118
dc.identifier.scopus2-s2.0-84869882813en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage582en_US
dc.identifier.urihttps://doi.org/10.1016/j.apenergy.2012.06.040
dc.identifier.urihttps://hdl.handle.net/20.500.12491/7730
dc.identifier.volume101en_US
dc.identifier.wosWOS:000312617400065en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.institutionauthorÇelik, Ali Naci
dc.language.isoenen_US
dc.publisherElsevier Sci Ltden_US
dc.relation.ispartofApplied Energyen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectWind Speed Distributionen_US
dc.subjectWind Speed Probability Functionen_US
dc.subjectGeneralized Feed-Forward Neural Network (GFNN)en_US
dc.subjectWeibull Functionen_US
dc.subjectWind Energyen_US
dc.titleGeneralized feed-forward based method for wind energy predictionen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
ali-naci-celik-7730.pdf
Boyut:
699.36 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam metin/Full text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Makine Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu