A Novel Short-Term Photovoltaic Power Forecasting Approach based on Deep Convolutional Neural Network

Basit Öğe Kaydı
dc.authorid0000-0002-5159-0659en_US
dc.contributor.authorKorkmaz, Deniz
dc.contributor.authorAçıkgöz, Hakan
dc.contributor.authorYıldız, Ceyhun
dc.date.accessioned2022-03-22T11:22:56Z
dc.date.available2022-03-22T11:22:56Z
dc.date.issued2021en_US
dc.departmentMTÖ Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.description.abstractIn this study, a novel photovoltaic power forecasting system that utilizes a deep Convolutional Neural Network (CNN) structure and an input signal decomposition algorithm is proposed. The proposed CNN architecture extracts deep features to forecast short-term power using transfer learning-based AlexNet. The historical power, solar radiation, wind speed, and temperature data are selected as the input. The signal decomposition algorithm called Empirical Mode Decomposition (EMD) is utilized to decompose the historical power signal into sub-components. In order to extract deep features, all input parameters are converted to 2D feature maps and feed to the input of the CNN. The experiments are realized on a grid-tied Photovoltaic Power Plant (PVPP) that has 1000 kW installed capacity located in Turkey. The experiments are performed under four weather conditions as partial cloudy, cloudy-rainy, heavy-rainy, and sunny days to show the effectiveness of the proposed method. The obtained results are compared with the benchmark regression algorithms. When the results are analyzed, the proposed method gives the highest Correlation Coefficient (R) and the lowest Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and SMAPE values under all horizons and weather conditions. For 1-h to 5-h ahead, the average R values of the proposed method are obtained as 97.28%, 95.77%, 94.49%, 93.61%, and 92.62%, respectively. The average RMSE values are observed as 4.90%, 6.30%, 7.50%, 8.00%, and 9.17% for 1-h to 5-h ahead. The experimental results confirm that the proposed method outperforms the conventional regression algorithms and reveals effective results with its competitive performance.en_US
dc.identifier.citationKorkmaz, D., Acikgoz, H., & Yildiz, C. (2021). A novel short-term photovoltaic power forecasting approach based on deep convolutional neural network. International Journal of Green Energy, 18(5), 525-539.en_US
dc.identifier.doi10.1080/15435075.2021.1875474
dc.identifier.endpage539en_US
dc.identifier.issue5en_US
dc.identifier.scopus2-s2.0-85100245633en_US
dc.identifier.startpage525en_US
dc.identifier.urihttps://doi.org/10.1080/15435075.2021.1875474
dc.identifier.urihttps://hdl.handle.net/20.500.12899/762
dc.identifier.volume18en_US
dc.identifier.wosWOS:000613788300001en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.institutionauthorKorkmaz, Deniz
dc.language.isoenen_US
dc.relation.ispartofInternational Journal of Green Energyen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectPhotovoltaic power planten_US
dc.subjectphotovoltaic power forecastingen_US
dc.subjectconvolutional neural networken_US
dc.subject,empirical mode decompositionen_US
dc.subjectdeep learningen_US
dc.titleA Novel Short-Term Photovoltaic Power Forecasting Approach based on Deep Convolutional Neural Networken_US
dc.typeArticleen_US

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu