Forecasting of Renewable Energy Generation for Turkey by Artificial Neural Networks and ARIMA Model: 2023 Generation Targets by Renewable Energy Resources

Yıl 2023, Cilt: 57 Sayı: 1, 121 - 138, 31.01.2023

Özlem Karadağ Albayrak

https://doi.org/10.51551/verimlilik.1031367

Cited By: 2

Öz

Purpose: Türkiye attaches particular importance to the energy production with renewable energy sources in order to overcome the negative economic, environmental and social effects which are caused by fossil resources in energy production. The aim of this study is to propose a model for forecasting the amount of energy to be produced for Türkiye using renewable energy resources.

Methdology: In this study, a forecasting model was created by using the generatio amount of energy generation from renewable sources data between 1965 and 2019 and by using Artificial Neural Networks (ANN) and Autoregressive Integrated Moving Average (ARIMA) methods.

Findings: While it was estimated that 127.516 TWh of energy will be produced in 2023 with the ANN method, this amount was estimated as 45,457 TeraWatt Hours (TWh) with the ARIMA (1,1,6) model. Mean Absolute Percent Error (MAPE) was calculated in order to determine the margin of error of the forecasting models. These values were determined as 13.1% for the ANN model and 21.9% for the ARIMA model. These results show that the ANN model gives a more appropriate estimation result.

Originality: In this research, a new model was proposed for the amount of energy to be obtained from RES in Türkiye. It is thought that the results obtained in this study will be useful in energy planning and management.

Anahtar Kelimeler

Renewable Energy Sources, Renewable Energy Generation Forecast, Artificial Neural Networks, ARIMA Model, Time Series Forecast

Yapay Sinir Ağları ve ARIMA Modeli ile Türkiye Için Yenilenebilir Enerji Üretiminin Tahmini: 2023 Yenilenebilir Enerji Kaynaklarına Göre Üretim Hedefleri

Öz

Amaç: Türkiye, enerji üretiminde fosil kaynakların neden olduğu olumsuz ekonomik, çevresel ve sosyal etkileri ortadan kaldırmak için yenilenebilir enerji kaynakları ile enerji üretimine ve tahminine çok önem vermektedir. Bu çalışmanın amacı, Yenilenebilir enerji kaynakları kullanılarak Türkiye’de üretecek enerji miktarını tahmin etmek için bir model önermektir.

Yöntem: Bu araştırma 1965-2019 yılları arasında yenilenebilir kaynaklı enerji üretim verileri kullanılarak Yapay Sinir Ağları (YSA) ve Otoregresif Bütünleşik Hareketli Ortalama (ARIMA) yöntemlerinden yararlanılmıştır.

Bulgular: ANN yönteminde, 2023 yılında 127.516 TWh enerji üretileceği tahminedilirken, ARIMA (1.1.6) modeli ile bu miktarın 45.457 TeraWatt Saat (TWh) olacağı tahmin edilmiştir. Tahmin modellerinin hata payını belirlemek için Ortalama Mutlak Yüzde Hatası (MAPE) hesaplanmıştır. Bu değer YSA modeli ile %13,1, ARIMA modeli ile %21,9 olarak belirlenmiştir. YSA modelinin daha doğru bir sonuç verdiğini göstermiştir.

Özgünlük: Türkiye’de YEK’dan elde edilecek enerji miktarı tahmini için model önerisi yapılmıştır. Bu çalışmada ulaşılan sonuçların enerji planlaması ve yönetiminde faydalı olacağı düşünülmektedir.

Anahtar Kelimeler

Enerji, Yenilenebilir Enerji Kaynakları, Yenilenebilir Enerji Üretimi Tahmini, Yapay Sinir Ağları, ARIMA Modeli, Zaman Serisi Tahmini

Kaynakça

• Abdirassilov, Z., Sładkowski, A. (2018). “Application of Artificial Neural Networks for Shortterm Prediction of Container Train Flows in Direction of China-Europe via Kazakhstan”, Transport Problems, 13(4): 103-113.
• Ahmad Tzhanga, H., Yana, B. (2020). “A Review on Renewable Energy and Electricity Requirement Forecasting Models for Smart Grid and Buildings”, Sustainable Cities and Society, 55, 102052.
• Alkan, O., Albayrak, O.K. (2020), “Ranking of Renewable Energy Sources for Regions in Turkey by Fuzzy Entropy Based Fuzzy COPRAS and Fuzzy MULTIMOORA”, Renewable Energy, 162, 712-726. https://doi.org/10.1016/j.renene.2020.08.062.
• Araujo da Silva Junior, J.C., Michaelsen, A.L., Scalvi, M., Pacheco, M.T.G. (2018). “ Forecast of Electric Energy Generation Potential from Swine Manure in Santa Catarina, Brazil, Environment”, Development and Sustainability, 22 (3): 2305-2319.
• Asensio, J.J., Darado, F. , Duran, J. (2020). “Energy Demand Forecasting Using Deep Learning: Applications for the French Grid”, Energies, 13: 2242-2257.
• Box, G.E.P., Jenkins, G.M. (1976). sTime series analysis. Forecasting and Controls. Revised edition. San Francisco: Holden Day.
• Bhardwaj, S., Chandrasekhar. E., Padiyar, P., Gadre, V.M. (2020). “A Comparative Study of Wavelet-Based ANN and Classical Techniques for Geophysical Time-Series Forecasting”, Computers & Geosciences, 138, 104461.
• BP (2020). “Statistical Review of World Energy 2020”, https://www.bp.com/content/dam/bp/business-sites/en/global/corporate/pdfs/energy-economics/statistical-review/bp-stats-review-2020-full-report.pdf, (Access Date: 01.10.2020)
• Broadny, J., Tutak. M., Saki, S.A. (2020). “Forecasting the Structure of Energy Production from Renewable Energy Sources and Biofuels in Poland”, Energies, 13, 2539-2570.
• Cengiz, C., Manga, M. (2021).” The Causal Linkages between Renewable Energy Consumption, Economic Growth, Oil Prices and CO2 Emissions in Selected OECD Countries”, Verimlilik Dergisi, 3, 165-183.
• Cinar, D., Kayakutlu, G. (2007). “Forecasting Production of Renewable Energy Using Cognitive Mapping and Artificial Neural Networks”, 19th International Conference on Production Research, Proceedings, Valparaiso, Chile
• Ediger, V.S., Akar, S. (2007). “ARIMA Forecasting of Primary Energy Demand by Fuel in Turkey”, Energy Policy, 35, 1701-1708.
• EPDK (2020). “Electricity Market Annual Sector Report”, https://www.epdk.gov.tr/Detay/Icerik/3-0-24/elektrikyillik-se%22ktor-raporu, (Access Date: 20.12.2022).
• Erdoğdu, E. (2007). “Electricity Demand Analysis Using Cointegration and ARIMA Modelling: A Case Study of Turkey”, Energy Policy, 35(2), 1129-1146.
• Fanoodi, B., Malmir, B., Jahantigh, F.F. (2019). “Reducing Demand Uncertainty in the Platelet Supply Chain Through Artificial Neural Networks and ARIMA Models”, Computers in Biology and Medicine, 113, 103415.
• Ghalehkhondabi. I., Ardjmand, E., Weckman, G.R., Young, W.A. (2016). “An Overview of Energy Demand Forecasting Methods Published in 2005–2015”, Energy Systems, 8(2),411-447.
• Han, X., Li, R.(2019). “Comparison of Forecasting Energy Consumption in East Africa Using the MGM, NMGM, MGM-ARIMA, and NMGM-ARIMA Model”, Energies, 12, 3278.
• Hu, H.,Wang, L., Lv, S.X . (2020), “Forecasting Energy Consumption and Wind Power Generation Using Deep Echo State Network”, Renewable Energy, 154, 598-613.
• Hu, Z., Ma, J.,Yang, L., Yao, L., Pang, M. (2019), “Monthly Electricity Demand Forecasting Using Empirical Mode Decomposition-Based State Space Model”, Energy & Environment, 30(7), 1-19.
• Jahanshahi, A., Jahanianfard, D., Mostafaie, A., Kamali, M. (2019). “An Auto Regressive Integrated Moving Average (ARIMA) Model for Prediction of Energy Consumption by Household Sector in Euro Area”, AIMS Energy, 7(2), 151-164.
• Jamil, R. (2020). “Hydroelectricity Consumption Forecast for Pakistan Using ARIMA Modeling and Supply-Demand Analysis for the Year 2030”, Renewable Energy, 54, 1-10.
• Jasinski, T., Marszal, A., Bochenek, A., (2016). “Selected Applications Artificial Neural Networks on the Currency Market, Forward Market and in Spatial Economy”; Politechnika Lodzka, Lodz, Poland.
• Kankal, M., Akpinar, A., Komurcu, M.I., Ozsahin, T.S. (2011). “Modeling and Forecasting of Turkey’s Energy Consumption Using Socio-Economic and Demographic Variables”, Applied Energy, 88, 1927-1939.
• Kazemzadeh, M.R., Amjadian, A., Amraee, T. (2020). “A Hybrid Data Mining Driven Algorithm for Long Term Electric Peak Load And Energy Demand Forecasting”, Energy, 204,117948.
• Kheirkhah, A., Azadeh, A., Saberı, M., Azaron, A., Shakourı H. (2013). “Improved Estimation of Electricity Demand Function by Using of Artificial Neural Network, Principal Component Analysis and Data Envelopment Analysis”. Computers & Industrial Engineering, 64, 425-441.
• Mason, K., Duggan, J., Howley, E.. (2018). “Forecasting Energy Demand, Wind Generation and Carbon Dioxide Emissions in Ireland Using Evolutionary Neural Networks”, Energy, 155, 705-720.
• Naimoğlu, M., Akal, M. (2022). “Yükselen Ekonomilerde Enerji Etkinliğini Arz Yanli Etkileyen Faktörler”, Verimlilik Dergisi, 1, 16-31.
• Nair, K.R., Vanitha, V., Jisma, M. (2017). “Forecasting of Wind Speed Using ANN, ARIMA and Hybrid Models”, 2017 International Conference on Intelligent Computing,Instrumentation and Control Technologies (ICICICT). 6-7 July 2017, Kannur, Kerala, India.
• Oliveira, E.M., Oliveira, F.L.C. (2018). “Forecasting Mid-Long Term Electric Energy Consumption through Bagging ARIMA and Exponential Smoothing Methods”, Energy, 144, 776-788.
• Şahin, U. (2018). “Forecasting of Turkey’s Electricity Generation and CO2 Emissions in Estimating Capacity Factor”, Environmental Progress & Sustainable Energy, 38(1), 56-65.
• Şahin, U. (2020). “Projections of Turkey’s Electricity Generation and Installed Capacity from Total Renewable and Hydro Energy Using Fractional Nonlinear Grey Bernoulli Model and Its Reduced Forms”, Sustainable Production and Consumption, 23, 52-62.
• Shireena, T., Shaob, C., Wanga, H., Lic, J., Zhangd, X., Lie, M. (2018). “Iterative Multi-Task Learning for Time-Series Modeling of Solar Panel PV Outputs”, Applied Energy, 212, 654-662.
• Sozen, A., Arcaklioglu, E. (2007). “Prospects for Future Projections of the Basic Energy Sources in Turkey”, Energy Sources, Part B: Economics, Planning, and Policy, 2, 183-201.
• Suganthia, L., Samuel, A.A. (2012). “Energy Models for Demand Forecasting-A Review”, Renewable and Sustainable Energy Reviews, 16, 1223-1240.
• Uzlu, E., Akpınar, A., Özturk, H.T., Nacar, S., Kankal, M. (2014). “Estimates of Hydroelectric Generation Using Neural Networks with the Artificial Bee Colony Algorithm for Turkey”, Energy, 69, 638-647.
• Wang, Z.X., Wang, Z.W., Li, Q. (2020). “Forecasting the Industrial Solar Energy Consumption Using a Novel Seasonal GM(1,1) Model with Dynamic Seasonal Adjustment Factors”, Energy, 200, 117460.
• Wei, Y., Chen, M.C. (2012). “Forecasting the Short-Term Metro Passenger Flow with Empirical Mode Decomposition and Neural Networks”, Transportation Research Part C, 21, 148-162.
• YEKDEM (2020). “Renewable Energy Resources Support Mechanism”, https://www.epdk.gov.tr/Detay/Icerik/3-0-0-122/yenilenebilir-enerji-kaynaklari-destekleme-mekanizmasi-yekdem, (Access Date: 14.12. 2020).
• Zolfani, S.H., Saparauskas, J. (2013). “New Application of SWARA Method in Prioritizing Sustainability Assessment Indicators of Energy System”, Engineering Economics, 24(5), 408-414.