One-day ahead forecasting of energy production from run-of-river hydroelectric power plants with a deep learning approach

Basit Öğe Kaydı
dc.authoridBilgili, Mehmet/0000-0002-5339-6120
dc.authoridKeiyinci, Sinan/0000-0003-2948-3846
dc.authoridekinci, firat/0000-0002-4888-7881
dc.contributor.authorBilgili, M.
dc.contributor.authorKeiyinci, S.
dc.contributor.authorEkinci, F.
dc.date.accessioned2025-01-06T17:36:05Z
dc.date.available2025-01-06T17:36:05Z
dc.date.issued2022
dc.description.abstractAccurate energy production forecasting is critical when planning energy for the economic development of a country. A deep learning approach based on Long Short-Term Memory (LSTM) to predict one-day-ahead energy production from the run-of-river hydroelectric power plants in Turkey was introduced in the present study. Furthermore, to compare the prediction accuracy, the methods of Adaptive Neuro-Fuzzy Inference System (ANFIS) with Fuzzy C-Means (FCM), ANTIS with Subtractive Clustering (SC), and ANFIS with Grid Partition (GP) were utilized. The predicted values obtained by the application of these four methods were evaluated with detected values. The correlation coefficient (R), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPS), and Root Mean Square Error (RMSE) were used as quality metrics for prediction. The comparison showed that the LSTM neural network provided higher accuracy results in short-term energy production prediction than other ANFIS models used in the study. (C) 2022 Sharif University of Technology. All rights reserved.
dc.description.sponsorshipCukurova University Scientific Research Project Coordination [FBA2019-11937]
dc.description.sponsorshipThe authors would like to thank the Cukurova University Scientific Research Project Coordination (FBA2019-11937) for financial support.
dc.identifier.doi10.24200/sci.2022.58636.5825
dc.identifier.endpage1852
dc.identifier.issn1026-3098
dc.identifier.issue4
dc.identifier.scopus2-s2.0-85137708875
dc.identifier.scopusqualityQ2
dc.identifier.startpage1838
dc.identifier.urihttps://doi.org/10.24200/sci.2022.58636.5825
dc.identifier.urihttps://hdl.handle.net/20.500.14669/1753
dc.identifier.volume29
dc.identifier.wosWOS:000844003500007
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSharif Univ Technology
dc.relation.ispartofScientia Iranica
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241211
dc.subjectAdaptive Neuro-Fuzzy Inference System (ANFIS)
dc.subjectDeep learning
dc.subjectEnergy production
dc.subjectLong Short-Term Memory (LSTM)
dc.subjectRun-of-river hydroelectric power plant
dc.titleOne-day ahead forecasting of energy production from run-of-river hydroelectric power plants with a deep learning approach
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu