Electric Energy Consumption Forecast And Analysis For Duzce Province
Küçük Resim Yok
Tarih
2025
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
The purpose of this study is to develop estimation models for the electrical energy consumption values of Düzce Province, Turkey. It has been demonstrated that estimation models were constructed and analyzed for the electrical energy consumption of Düzce between November 2019 and October 2021. To create the dataset, data were obtained monthly from Enerji Piyasaları İşletme A.Ş. (EPİAŞ). Since the data cover two periods (12 months and 24 months) and include seasonality, the Least Squares Method, Fourier Analysis, and Winters' Method were chosen as the estimation models. The evaluation of the models using the Mean Absolute Percentage Error (MAPE) method indicates that Fourier Analysis performs worse than Winters' Method. Winters' Method, which is a multiplicative model, achieved better performance in constructing the electrical energy consumption estimation model in this study. When comparing the two estimation models, no significant difference was observed; however, the analysis results reveal that Winters' Method is more favorable for forecasting electricity consumption values in Düzce for the period between November 2019 and October 2021. These findings demonstrate that Winters' Method outperforms both the Least Squares Method and Fourier Analysis, making it a more reliable option for future studies focused on constructing electricity consumption estimation models. This result emphasizes the importance of using Winters' Method as a reference for future research on electricity demand forecasting.
Açıklama
Anahtar Kelimeler
Energy Consumption, Estimation, Time Series, Fourier Analysis, Winters' Method
Kaynak
Journal of Yasar University
WoS Q Değeri
Scopus Q Değeri
Cilt
20
Sayı
77
