Prediction of mean monthly wind speed and optimization of wind power by artificial neural networks using geographical and atmospheric variables: case of Aegean Region of Turkey

dc.authoridGünay, M. Erdem/0000-0003-1282-718X;
dc.authorwosidGünay, M. Erdem/I-1564-2019
dc.authorwosidKidane, Halefom/AAV-2476-2020
dc.contributor.authorUlkat, Deniz
dc.contributor.authorGunay, M. Erdem
dc.date.accessioned2024-07-18T20:40:37Z
dc.date.available2024-07-18T20:40:37Z
dc.date.issued2018
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description.abstractAlthough there are many locations suitable to construct new wind turbines, wind speeds in those areas are not always available, which makes it difficult to plan and develop a proper wind energy conversion system. This paper proposes an approach to determine the wind speeds corresponding to locations without any past wind speed data. First, monthly mean wind speed was modeled as a function of geographical variables (latitude, longitude and elevation), atmospheric variables (ambient temperature, atmospheric pressure, percent relative humidity), and the month of the year for a case location (Aegean Region of Turkey) by artificial neural networks (ANNs) trained by the data supplied by 55 wind speed measuring stations throughout the region (660 data points). Then, the prediction ability of the ANN model was tested: The wind speed data of each station was excluded from the database, and an ANN model trained by the data of the rest of the wind stations was used to forecast the excluded data. Finally, a grid search algorithm was applied to the entire region to search for the optimum location for the maximum average annual wind speed which was found to be 10.6m/s. A generic wind turbine was considered at this location and a power of 1.79MW was achieved.en_US
dc.identifier.doi10.1007/s00521-017-2895-x
dc.identifier.endpage3048en_US
dc.identifier.issn0941-0643
dc.identifier.issn1433-3058
dc.identifier.issue10en_US
dc.identifier.scopus2-s2.0-85013846226en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage3037en_US
dc.identifier.urihttps://doi.org/10.1007/s00521-017-2895-x
dc.identifier.urihttps://hdl.handle.net/11411/7140
dc.identifier.volume30en_US
dc.identifier.wosWOS:000449522000007en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer London Ltden_US
dc.relation.ispartofNeural Computing & Applicationsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectArtificial Neural Networksen_US
dc.subjectGeographical Variablesen_US
dc.subjectWind Speed Predictionen_US
dc.subjectRenewable Energyen_US
dc.subjectForecastingen_US
dc.subjectGrid Searchen_US
dc.subjectEmpirical Mode Decompositionen_US
dc.subjectReference Stations Dataen_US
dc.subjectSpatial Estimationen_US
dc.subjectTarget Stationen_US
dc.subjectWaveleten_US
dc.titlePrediction of mean monthly wind speed and optimization of wind power by artificial neural networks using geographical and atmospheric variables: case of Aegean Region of Turkeyen_US
dc.typeArticleen_US

Dosyalar