Renewable Energy Forecasting in Turkey: Analytical Approaches

Yıl 2025, Cilt: 8 Sayı: 1, 25 - 34

Mehmet Berke Colak , Erkan Özhan

https://doi.org/10.38016/jista.1447980

Öz

The growing population and industrialization have resulted in an increased demand for energy, which has worsened environmental problems such as pollution and climate change. Renewable energy sources are considered a promising solution due to their environmental benefits and limited potential. This study examines the use of neural networks and time series analysis to predict electricity generation rates from renewable energy sources in Turkey. We use the LSTM, NNAR, and ELM models, all of which utilize the backpropagation algorithm for neural network forecasting. Additionally, we apply ARIMA, Holt’s trend, linear regression, mean, and exponential smoothing models for time series analysis. We evaluate the performance using the mean absolute error and root mean square error on the training and test data. The study showed that LSTM models outperformed the ARIMA (1,2,1), ARIMA (2,2,1), ARIMA (3,2,1), and NNAR methods in forecasting accuracy. Although the NNAR model initially had the lowest error, its linear predictions made it less suitable for practical applications. This study highlights the effectiveness of neural networks and time series analysis in predicting renewable energy sources. The ARIMA (1,2,1), LSTM and ARIMA (3,2,1) modeling methods are useful for optimizing the planning and management of Turkey's renewable energy future, contributing to a more sustainable energy landscape.

Anahtar Kelimeler

Renewable energy, Turkey, time series, neural networks, climate change, ARIMA, LSTM

Türkiye'de Yenilenebilir Enerji Tahmini: Analitik Yaklaşımlar

Öz

Artan nüfus ve sanayileşme, enerji talebinin artmasına neden olmuş, bu da kirlilik ve iklim değişikliği gibi çevre sorunlarını daha da kötüleştirmiştir. Yenilenebilir enerji kaynakları, çevresel faydaları ve sınırsız potansiyelleri nedeniyle ümit verici bir çözüm olarak değerlendirilmektedir. Bu çalışma, Türkiye'de yenilenebilir enerji kaynaklarından elektrik üretim oranlarını tahmin etmek için sinir ağlarının ve zaman serisi analizinin kullanımını incelemektedir. Sinir ağı tahminleri için her ikisi de geri yayılım algoritmasını temel alan LSTM, NNAR ve ELM modellerini kullanıyoruz. Ayrıca zaman serisi analizi için ARIMA, Holt trendi, doğrusal regresyon, ortalama ve üstel düzeltme modellerini kullanıyoruz. Performansı, eğitim ve test verilerinde ortalama mutlak hata ve kök ortalama kare hata kullanarak değerlendiriyoruz. Çalışma, LSTM modellerinin tahmin doğruluğunda ARIMA (1,2,1), ARIMA (2,2,1), ARIMA (3,2,1) ve NNAR yöntemlerinden daha iyi performans gösterdiğini göstermiştir. NNAR modeli başlangıçta en düşük hataya sahip olmasına rağmen doğrusal tahminleri onu pratik uygulamalar için daha az uygun hale getirdi. Çalışma, yenilenebilir enerji kaynaklarının tahmin edilmesinde sinir ağlarının ve zaman serisi analizinin etkinliğini vurguluyor. ARIMA (1,2,1), LSTM ve ARIMA (3,2,1) modelleme yöntemleri, Türkiye'nin yenilenebilir enerji geleceğinin planlanması ve yönetimini optimize etmek ve daha sürdürülebilir bir enerji ortamına katkıda bulunmak için kullanışlıdır.

Anahtar Kelimeler

Yenilenebilir enerji, Türkiye, zaman serileri, sinir ağları, iklim değişikliği, ARIMA, LSTM

Kaynakça

• Akusok, A., 2016. Extreme Learning Machines : novel extensions and application to Big Data. University of Iowa Iowa Research Online,A thesis submitted in partial fulfillment of the requirements for the Doctor of Philosophy degree in Industrial Engineering in the Graduate College of The University of Iowa.
• Baccar, Y.B., 2019. Comparative Study on Time Series Forecasting Models. Master of Science (Data Science)Advisor: Bertrand Lamy, Jacques Doan HUU 1–92. https://doi.org/10.13140/RG.2.2.32241.02408
• Baskan, S., 2008. Effect Of Ligand Binding On Protein Dynamics : A Time Series Analysis. Bogazici University 77.
• Bouquet, P., Jackson, I., Nick, M., Kaboli, A., 2024. AI-based forecasting for optimised solar energy management and smart grid efficiency. International Journal of Production Research 62, 4623–4644. https://doi.org/10.1080/00207543.2023.2269565
• Box, G.E.P., Jenkins, G.M., Reinsel, G.C., Ljung, G.M., 1994. Time Series Analysis Forecasting and Control.
• Cakir, S., 2023. Renewable energy generation forecasting in Turkey via intuitionistic fuzzy time series approach. Renewable Energy 214, 194–200. https://doi.org/10.1016/j.renene.2023.05.132
• Çetin, Ö., Işık, A.H., 2021. Monthly Electricity Generatıon Forecast in Solar Power Plants with LSTM. Düzce Üniversitesi Bilim ve Teknoloji Dergisi 9, 55–64. https://doi.org/10.29130/dubited.1015251
• Daniyal, M., Tawiah, K., Muhammadullah, S., Opoku-Ameyaw, K., 2022. Comparison of Conventional Modeling Techniques with the Neural Network Autoregressive Model (NNAR): Application to COVID-19 Data. Journal of Healthcare Engineering 2022, 1–9. https://doi.org/10.1155/2022/4802743
• Erdem, K., 2020. Introduction to Extreme Learning Machines | by Kemal Erdem (burnpiro) | Towards Data Science.
• Ertürk, S., Kara, H., Akkus, C., Genc, G., 2023. Turkiye’de Farklı İklim Kuşakları İçin Yapay Sinir Ağları Kullanılarak Güneş Isınımının Tahmini. Gazi University Journal of Science Part C: Design and Technology 11, 885–892. https://doi.org/10.29109/gujsc.1331788
• Ghislieri, M., Cerone, G.L., Knaflitz, M., Agostini, V., 2021. Long short-term memory (LSTM) recurrent neural network for muscle activity detection. Journal of NeuroEngineering and Rehabilitation 18, 1–15. https://doi.org/10.1186/s12984-021-00945-w
• Gibson, K., 2020. The Application Of Machine Learning For Grounwater Level Prediction In The Steenkoppies Compartment Of The Gauteng And North West Dolomite Aquifer , South Africa.
• Golestaneh, F., Pinson, P., Gooi, H.B., 2016. Very short-term nonparametric probabilistic forecasting of renewable energy generation - With application to solar energy. IEEE Transactions on Power Systems 31, 3850–3863. https://doi.org/10.1109/TPWRS.2015.2502423
• Goncalves, C., Bessa, R.J., Pinson, P., 2021. Privacy-preserving Distributed Learning for Renewable Energy Forecasting. IEEE Transactions on Sustainable Energy 3029, 1–10. https://doi.org/10.1109/TSTE.2021.3065117
• Guang-Bin Huang, Qin-Yu Zhu, Chee-Kheong Siew, 2004. Extreme learning machine: a new learning scheme of feedforward neural networks, in: 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541). Presented at the 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), IEEE, Budapest, Hungary, pp. 985–990. https://doi.org/10.1109/IJCNN.2004.1380068
• Güllü, M., Kartal, Z., 2021. Türkiye’nin Yenilenebilir Enerji Kaynaklarının 2030 Yılına Kadar Tahmini. 19 Mayis Sosyal Bilimler Dergisi 2, 288–313. https://doi.org/10.52835/19maysbd.849978
• Hersh, M.A., 2006. The Economics and Politics of Energy Generation. IFAC Proceedings Volumes 39, 73–78. https://doi.org/10.1016/S1474-6670(17)30097-6
• Hocaoglu, F.O., Karanfil, F., 2013a. A time series-based approach for renewable energy modeling. Renewable and Sustainable Energy Reviews 28, 204–214. https://doi.org/10.1016/j.rser.2013.07.054
• Hocaoglu, F.O., Karanfil, F., 2013b. A time series-based approach for renewable energy modeling. Renewable and Sustainable Energy Reviews 28, 204–214. https://doi.org/10.1016/j.rser.2013.07.054
• Hochreiter, S., Schmidhuber, J., 1997. Long Short-Term Memory. Neural Computation 9, 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
• Jiang, P., Dong, J., Huang, H., 2019. Forecasting China’s renewable energy terminal power consumption based on empirical mode decomposition and an improved extreme learning machine optimized by a bacterial foraging algorithm. Energies 12. https://doi.org/10.3390/en12071331
• Kaysal, K., Yurttakal, A.H., Hocaoğlu, F.O., 2023. Hibrit derin öğrenme yöntemi kullanılarak hiperparametre optimizasyonu ile yenilenebilir elektrik enerjisi tahmini. Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi 12, 770–777. https://doi.org/10.28948/ngumuh.1263782
• Lanovaz, M.J., Adams, B., 2019. Comparing the Communication Tone and Responses of Users and Developers in Two R Mailing Lists: Measuring Positive and Negative Emails. IEEE Software 36, 46–50. https://doi.org/10.1109/MS.2019.2922949
• Lindemann, B., Müller, T., Vietz, H., Jazdi, N., Weyrich, M., 2021. A survey on long short-term memory networks for time series prediction. Procedia CIRP 99, 650–655. https://doi.org/10.1016/j.procir.2021.03.088
• Maleki, A., Nasseri, S., Aminabad, M.S., Hadi, M., 2018. Comparison of ARIMA and NNAR Models for Forecasting Water Treatment Plant’s Influent Characteristics. KSCE Journal of Civil Engineering 22, 3233–3245. https://doi.org/10.1007/s12205-018-1195-z
• Mossalam, A., Arafa, M., 2018. Using artificial neural networks (ANN) in projects monitoring dashboards’ formulation. HBRC Journal 14, 385–392. https://doi.org/10.1016/j.hbrcj.2017.11.002
• Mrutyunjaya, P., 2020. Application of ARIMA and Holt-Winters forecasting model to predict the spreading of COVID-19 for India and its states. Department of Computer and Applications, Utkal University, Vani Vihar, India 14, 1–4.
• Nastos, P.T., Moustris, K.P., Larissi, I.K., Paliatsos, A.G., 2013. Rain intensity forecast using Artificial Neural Networks in Athens, Greece. Atmospheric Research 119, 153–160. https://doi.org/10.1016/j.atmosres.2011.07.020
• Nurhamidah, N., Nusyirwan, N., Faisol, A., 2020. Forecasting Seasonal Time Series Data Using the Holt-Winters Exponential Smoothing Method of Additive Models. Jurnal Matematika Integratif 16, 151. https://doi.org/10.24198/jmi.v16.n2.29293.151-157
• Nyatuame, M., Agodzo, S.K., 2018. Stochastic ARIMA model for annual rainfall and maximum temperature forecasting over Tordzie watershed in Ghana. Journal of Water and Land Development 37, 127–140. https://doi.org/10.2478/jwld-2018-0032
• Olah, C., 2015. Understanding LSTM Networks.
• Paoli, C., Voyant, C., Muselli, M., Nivet, M.L., 2010a. Forecasting of preprocessed daily solar radiation time series using neural networks. Solar Energy 84, 2146–2160. https://doi.org/10.1016/j.solener.2010.08.011
• Paoli, C., Voyant, C., Muselli, M., Nivet, M.L., 2010b. Forecasting of preprocessed daily solar radiation time series using neural networks. Solar Energy 84, 2146–2160. https://doi.org/10.1016/j.solener.2010.08.011
• Rajni, Banerjee, T., Kumar, P., 2024. Forecasting of renewable energy production in United States: An ARIMA based time series analysis. AIP Conference Proceedings 3010, 030014. https://doi.org/10.1063/5.0193938
• Renewable energy explained - U.S. Energy Information Administration (EIA) [WWW Document], 2023. . EIA. URL https://www.eia.gov/energyexplained/renewable-sources/ (accessed 1.15.24).
• Sadia, I., Mahmood, A., Binti Mat Kiah, L., Azzuhri, S.R., 2022. Analysis and Forecasting of Blockchain-based Cryptocurrencies and Performance Evaluation of TBATS, NNAR and ARIMA, in: 2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET). Presented at the 2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), IEEE, Kota Kinabalu, Malaysia, pp. 1–6. https://doi.org/10.1109/IICAIET55139.2022.9936798
• Solano, E.S., Dehghanian, P., Affonso, C.M., 2022. Solar Radiation Forecasting Using Machine Learning and Ensemble Feature Selection. Energies 15, 7049. https://doi.org/10.3390/en15197049
• Tharani, K., Kumar, N., Srivastava, V., Mishra, S., Pratyush Jayachandran, M., 2020. Machine learning models for renewable energy forecasting. Journal of Statistics and Management Systems 23, 171–180. https://doi.org/10.1080/09720510.2020.1721636
• Van Houdt, G., Mosquera, C., Nápoles, G., 2020. A review on the long short-term memory model. Artif Intell Rev 53, 5929–5955. https://doi.org/10.1007/s10462-020-09838-1
• Yang, Q., Wang, J., Ma, H., Wang, X., 2020. Research on COVID-19 based on ARIMA modelΔ—Taking Hubei, China as an example to see the epidemic in Italy. Journal of Infection and Public Health 13, 1415–1418. https://doi.org/10.1016/j.jiph.2020.06.019
• Yük Tevzi Bilgi Sistemi (YTBS)-Türkiye Elektrik İstatistikleri [WWW Document], 2023. . Yük Tevzi Bilgi Sistemi (YTBS). URL https://ytbsbilgi.teias.gov.tr/ytbsbilgi/frm_istatistikler.jsf (accessed 1.15.24).