Araştırma Makalesi
BibTex RIS Kaynak Göster

Time Series Installed Capacity Forecasting with Deep Learning Approach for Türkiye

Yıl 2024, Cilt: 39 Sayı: 3, 709 - 718, 03.10.2024
https://doi.org/10.21605/cukurovaumfd.1560142

Öz

Deep learning methods have been developed to solve different problems due to the complex nature of real-world problems. Accurate future forecasting of a country's installed capacity is also crucial for developing a good energy sustainability strategy for the country. In this paper, three different time series forecasting methods are used for forward forecasting of installed capacity: Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). Installed power values for the years 1923-2021 were used in the study. Then, future forecasts are made until 2030. The GRU model achieved the best RMSE in the testing phase compared to the LSTM and CNN models. Although CNN is successful during training, it has a higher RMSE during testing compared to GRU. While all models predict a potential increase in electricity capacity by 2030, GRU and LSTM predict a more significant increase up to this point compared to CNN.

Kaynakça

  • 1. Bilgili, M., Yildirim, A., Ozbek, A., Celebi, K., Ekinci, F., 2021. Long short-term memory (LSTM) neural network and adaptive neuro-fuzzy inference system (ANFIS) approach in modeling renewable electricity generation forecasting. International Journal of Green Energy, 18(6), 578-594.
  • 2. Sun, L., Liu, T., Xie, Y., Zhang, D., Xia, X., 2021. Real-time power prediction approach for turbine using deep learning techniques. Energy, 233, 121130.
  • 3. Wan, A., Chang, Q., Khalil, A. B., He, J., 2023. Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism. Energy, 282, 128274.
  • 4. Agga, A., Abbou, A., Labbadi, M., El Houm, Y., Ali, I.H.O., 2022. CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production. Electric Power Systems Research, 208, 107908.
  • 5. Chang, R., Bai, L., Hsu, C.H., 2021. Solar power generation prediction based on deep learning. Sustainable Energy Technologies and Assessments, 47, 101354.
  • 6. Anu Shalini, T., Sri Revathi, B., 2023. Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems. Automatika: Časopis za Automatiku, Mjerenje, Elektroniku, Računarstvo i Komunikacije, 64(1), 127-144.
  • 7. Al-Ali, E.M., Hajji, Y., Said, Y., Hleili, M., Alanzi, A.M., Laatar, A.H., Atri, M., (2023). Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model. Mathematics, 11(3), 676.
  • 8. Sozen, A., Arcaklioglu, E., Ozkaymak, M., 2005. Modelling of Turkey's net energy consumption using artificial neural network. International Journal of Computer Applications in Technology, 22(2-3), 130-136.
  • 9. Warkad, S.B., Khedkar, M.K., Dhole, G.M., 2012. Day-ahead AC-DC OPF-based nodal price prediction by artificial neural network (ANN) in a restructured electricity market. International Journal of Power and Energy Conversion, 3(1-2), 54-76.
  • 10. Olcay, K., Tunca, S.G., Özgür, M.A., 2024. Forecasting and performance analysis of energy production in solar power plants using long short-term memory (LSTM) and random forest models. IEEE Access.
  • 11. Aksu, İ.Ö., 2023. Next-month prediction of hourly solar irradiance based on long short-term memory network. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 38(1), 225-232.
  • 12. Luo, X., Zeng, B., Li, H., Zhou, W., 2021. Forecasting Chinese wind power installed capacity using a novel grey model with parameters combination optimization. Journal of Mathematics, 2021(1), 9200560.
  • 13. Li, S., Yang, X., Li, R., 2018. Forecasting China’s coal power installed capacity: A comparison of MGM, ARIMA, GM-ARIMA, and NMGM models. Sustainability, 10(2), 506.
  • 14. Chen, L., Liu, Z., Ma, N., 2019. Prediction and analysis of generation installed capacity in China. In IOP Conference Series: Earth and Environmental Science, 237(6), 062020, IOP Publishing.
  • 15. Turkish Electricity Transmission Corporation, 2024. https://www.teias.gov.tr.

Türkiye için Derin Öğrenme Yaklaşımı ile Zaman Serisi Kurulu Kapasite Tahmini

Yıl 2024, Cilt: 39 Sayı: 3, 709 - 718, 03.10.2024
https://doi.org/10.21605/cukurovaumfd.1560142

Öz

Gerçek dünya problemlerinin karmaşık yapısı nedeniyle farklı problemleri çözmek için derin öğrenme yöntemleri geliştirilmiştir. Ülkelere ait kurulu gücün doğru şekilde ileri tahmini de ülkenin iyi bir enerji sürdürülebilirliği stratejisi geliştirilmesi için büyük önem taşımaktadır. Bu makalede, kurulu gücün ileri tahmini için üç farklı zaman serisi tahmin yöntemi kullanılmıştır: Kapılı Tekrarlayan Birim (GRU), Evrişimli Sinir Ağı (CNN) ve Uzun Kısa Süreli Bellek (LSTM). Çalışmada 1923-2021 yıllarına ait kurulu güç değerleri kullanılmıştır. Daha sonra 2030 yılına kadar gelecek tahminleri yapılmıştır. GRU modeli, test aşamasında LSTM ve CNN modellerine göre, en iyi RMSE'yi elde ederek en doğru model olarak ortaya çıkmıştır. CNN eğitim sırasında başarılı olmasına rağmen, test sırasında GRU'ya kıyasla daha yüksek RMSE sergilemiştir. Tüm modeller 2030 yılına kadar elektrik kapasitesinde potansiyel bir artış öngörürken GRU ve LSTM, CNN'e kıyasla bu noktaya kadar daha belirgin bir artış öngörmüştür.

Kaynakça

  • 1. Bilgili, M., Yildirim, A., Ozbek, A., Celebi, K., Ekinci, F., 2021. Long short-term memory (LSTM) neural network and adaptive neuro-fuzzy inference system (ANFIS) approach in modeling renewable electricity generation forecasting. International Journal of Green Energy, 18(6), 578-594.
  • 2. Sun, L., Liu, T., Xie, Y., Zhang, D., Xia, X., 2021. Real-time power prediction approach for turbine using deep learning techniques. Energy, 233, 121130.
  • 3. Wan, A., Chang, Q., Khalil, A. B., He, J., 2023. Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism. Energy, 282, 128274.
  • 4. Agga, A., Abbou, A., Labbadi, M., El Houm, Y., Ali, I.H.O., 2022. CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production. Electric Power Systems Research, 208, 107908.
  • 5. Chang, R., Bai, L., Hsu, C.H., 2021. Solar power generation prediction based on deep learning. Sustainable Energy Technologies and Assessments, 47, 101354.
  • 6. Anu Shalini, T., Sri Revathi, B., 2023. Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems. Automatika: Časopis za Automatiku, Mjerenje, Elektroniku, Računarstvo i Komunikacije, 64(1), 127-144.
  • 7. Al-Ali, E.M., Hajji, Y., Said, Y., Hleili, M., Alanzi, A.M., Laatar, A.H., Atri, M., (2023). Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model. Mathematics, 11(3), 676.
  • 8. Sozen, A., Arcaklioglu, E., Ozkaymak, M., 2005. Modelling of Turkey's net energy consumption using artificial neural network. International Journal of Computer Applications in Technology, 22(2-3), 130-136.
  • 9. Warkad, S.B., Khedkar, M.K., Dhole, G.M., 2012. Day-ahead AC-DC OPF-based nodal price prediction by artificial neural network (ANN) in a restructured electricity market. International Journal of Power and Energy Conversion, 3(1-2), 54-76.
  • 10. Olcay, K., Tunca, S.G., Özgür, M.A., 2024. Forecasting and performance analysis of energy production in solar power plants using long short-term memory (LSTM) and random forest models. IEEE Access.
  • 11. Aksu, İ.Ö., 2023. Next-month prediction of hourly solar irradiance based on long short-term memory network. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 38(1), 225-232.
  • 12. Luo, X., Zeng, B., Li, H., Zhou, W., 2021. Forecasting Chinese wind power installed capacity using a novel grey model with parameters combination optimization. Journal of Mathematics, 2021(1), 9200560.
  • 13. Li, S., Yang, X., Li, R., 2018. Forecasting China’s coal power installed capacity: A comparison of MGM, ARIMA, GM-ARIMA, and NMGM models. Sustainability, 10(2), 506.
  • 14. Chen, L., Liu, Z., Ma, N., 2019. Prediction and analysis of generation installed capacity in China. In IOP Conference Series: Earth and Environmental Science, 237(6), 062020, IOP Publishing.
  • 15. Turkish Electricity Transmission Corporation, 2024. https://www.teias.gov.tr.
Toplam 15 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Modelleme ve Simülasyon
Bölüm Makaleler
Yazarlar

Zeynep Altıparmak 0009-0005-5887-0898

İnayet Özge Aksu 0000-0002-0963-2982

Yayımlanma Tarihi 3 Ekim 2024
Gönderilme Tarihi 25 Temmuz 2024
Kabul Tarihi 27 Eylül 2024
Yayımlandığı Sayı Yıl 2024 Cilt: 39 Sayı: 3

Kaynak Göster

APA Altıparmak, Z., & Aksu, İ. Ö. (2024). Time Series Installed Capacity Forecasting with Deep Learning Approach for Türkiye. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 39(3), 709-718. https://doi.org/10.21605/cukurovaumfd.1560142