Short-term forecasting of wind power generation using artificial intelligence

Basit Öğe Kaydı
dc.authorscopusid58209638600en_US
dc.authorscopusid25923035200en_US
dc.authorscopusid57301638100en_US
dc.authorscopusid58210076600en_US
dc.authorscopusid58713812800en_US
dc.authorscopusid57196825693en_US
dc.contributor.authorQureshi, S.
dc.contributor.authorShaikh, F.
dc.contributor.authorKumar, L.
dc.contributor.authorAli, F.
dc.contributor.authorAwais, M.
dc.contributor.authorGürel, A.E.
dc.date.accessioned2024-08-23T16:07:39Z
dc.date.available2024-08-23T16:07:39Z
dc.date.issued2023en_US
dc.departmentDüzce Üniversitesien_US
dc.description.abstractAs global warming is increasing due to conventional sources the government and the private sectors introduce policies to minimize it, renewable energy has been developed and deployed because of these strategies. Among the various renewable energy sources, wind energy is the fastest-growing and cleanest energy resource in the world. However, predicting wind power is not easy due to the nonlinearity in wind speed that eventually depends on weather conditions. To reduce these issues improved forecasting models have been used to get the correct results and improve the performance and stability of the power system and thereby its reliability and security. In this work, two models are used to predict the “Output of Wind Turbine” to improve the prediction accuracy of short-term wind power generation. The two models namely the Gated Recurrent Unit (GRU) from the deep learning model and Autoregressive Integrated Moving Average (ARIMA) from Statistical Learning. The data used in this research is collected from the wind power plant, Located in Jhimpir Pakistan. This study compares the accuracy metrics of deep learning models and statistical models to determine which model is the most effective for producing wind power. The results are obtained by using python programming in Jupyter Notebook software and the accuracy metrics of each algorithm are compared with each other as a result Gated recurrent unit (GRU) is the best model among others with the least possible errors and high accuracy. i.e., up to 0.047 root mean square error, 0.89 coefficient of metrics, and 0.03 mean absolute error. Hence, due to its advanced features, then other deep learning, and statistical models the Gated recurrent unit (GRU) Model is suitable for the prediction of wind turbine output power. © 2023 The Authorsen_US
dc.identifier.doi10.1016/j.envc.2023.100722
dc.identifier.issn2667-0100
dc.identifier.scopus2-s2.0-85154564102en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1016/j.envc.2023.100722
dc.identifier.urihttps://hdl.handle.net/20.500.12684/14757
dc.identifier.volume11en_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier B.V.en_US
dc.relation.ispartofEnvironmental Challengesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectartificial intelligenceen_US
dc.subjectautoregressive integrated moving averageen_US
dc.subjectgated recurrent uniten_US
dc.subjectshort-term forecastingen_US
dc.subjectWind power forecastingen_US
dc.titleShort-term forecasting of wind power generation using artificial intelligenceen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu