Modelling of Turkey’s Energy Consumption Using Artificial Neural Networks

Abstract:

Energy is one of the most important inputs to maintain social and economic improvement in the countries. It is necessary that energy demand should be performed at the right time economically and be of good quality and respectful if increasing environmental consciousness in order to preserve national development and a high standard of living. Turkey's energy use is expected to increase by 50% over the next decade. Turkey's installed capacity has exceeded 88 GW as of January 2019, representing a threefold increase in 15 years. For this reason, an accurate prediction of the consumed energy is critical. Predictions of energy demand in developing countries show more deviations than in developed countries. The essential scope of this study is to develop a new electricity prediction model for Turkey, which has not been used in the literature before. In the study, the global system for mobile communications (gsm) subscribers, fertility rate and cultivated land per capita have been used for the first time in the literature as variables. Factors resulting from health-ecological problems as well as cultural, social and economic changes and differences in Turkey were included in the model to obtain more realistic results. The model was developed between 1975 and 2016, and 73 different economic and social variables were evaluated using artificial neural networks (ANN). The model was established by reducing the number of variables according to the weight ratio. Then, two different cases have been created and tested. Turkey’s electricity consumption has been predicted accurately until 2023 using SPSS Clementine software.

• Periodical: Advanced Engineering Forum (Volume 44)
• Pages: 73-86
• DOI: https://doi.org/10.4028/www.scientific.net/AEF.44.73
• Online since: January 2022
• Authors: Nuri Şişman, Mehmet Alper Sofuoğlu*, Nil Aras, Haydar Aras
• Keywords: Artificial Neural Networks, Electricity Consumption Prediction, Forecasting Model, Turkey

References

[1] I.Karakurt, G.Aydın, K.Aydıner, Sources and mitigation of methane emissions by sector, a critical review, Renewable Energy 39(1) (2012) 40-48.

DOI: 10.1016/j.renene.2011.09.006

[2] R. Kızılaslan, B. Büyükkınacı, D. Bayraktar, D. Çelebi, Artificial neural networks and fuzzy logic model proposals for natural gas demand forecasting, 29th National Congress of Operations Research and Industrial Engineering, Ankara (22-May, 2009).

[3] L. Ekonomou, Greek long-term energy consumption prediction using artificial neural networks, Energy 35(2) (2010) 512-517.

DOI: 10.1016/j.energy.2009.10.018

[4] T. Limanond, S. Jomnonkwao, A. Srikaew, Projection of future transport energy demand of Thailand, Energy Policy 39 (5) (2011) 2754-2763.

DOI: 10.1016/j.enpol.2011.02.045

[5] M. Kankal, A. Akpınar, M.I. Kömürcü, T.Ş. Özşahin, Modeling and forecasting of Turkey's energy consumption using socioeconomic and demographic variables, Applied Energy 88 (5) (2011) 1927-1939.

DOI: 10.1016/j.apenergy.2010.12.005

[6] O. Kaynar, S. Taştan, F. Demirkoparan, Estimation of natural gas consumption by artificial neural networks, Atatürk Economic Administrative Sciences Journal 25 (4) (2011) 463-475.

[7] A. Sofuoğlu, H.Aras, Estimation of Energy and Water Consumption in Houses by Statistical Analysis and Artificial Neural Method, 12th International Econometric Operations Research and Statistical Symposium, Pamukkale University, Denizli (26-29th May, 2019).

[8] M. Bilgili, B. Şahin, A. Yaşar, E. Şimşek, Electric energy demands of Turkey in residential and industrial sectors, Renewable and Sustainable Energy Reviews 16 (1) (2012) 404- 414.

DOI: 10.1016/j.rser.2011.08.005

[9] H.A. Es, F.Y. Kalender, C. Harzemçebi, Forecasting the net energy demand of Turkey by artificial neural networks, Journal of the Faculty of Engineering and Architecture of Gazi University 20 (3) (2014) 495-504.

[10] M.Akdağ, V. Yiğit, Box-jenkins and artificial neural network models and inflation forecasting, Atatürk University Journal of Economics and Administrative Sciences 30 (2) (2016) 269-283.

[11] G.Aydın, H. Jang, E.Topal, Energy consumption modeling using artificial neural networks: The case of world's highest consumers, Energy Sources Part B: Economics, Planning, and Policy 11 (3) (2016) 212-219.

DOI: 10.1080/15567249.2015.1075086

[12] M.E. Günay, Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey, Energy Policy 90(3) (2016) 92-101.

DOI: 10.1016/j.enpol.2015.12.019

[13] C. Hamzaçebi, H.A. Es, R. Çakmak, Forecasting of Turkey's Monthly Electricity Demand by Seasonal Artificial Neural Network. Neural Computing and Applications, (2017) 1-15.

DOI: 10.1007/s00521-017-3183-5

[14] D.M. Toksarı, Estimating the net electricity energy generation and demand using the ant colony optimization approach: case of Turkey, Energy Policy 37(3) (2009) 1181-1187.

DOI: 10.1016/j.enpol.2008.11.017

[15] D.M. Toksarı, Ant colony optimization approach to estimate energy demand of Turkey, Energy Policy 35 (8) (2007) 3984-3990.

DOI: 10.1016/j.enpol.2007.01.028

[16] S.Öztürk, F. Öztürk, Forecasting Energy Consumption of Turkey by ARIMA Model, Model. Journal of Asian Scientific Research 8(2) (2018) 52-60.

[17] V.P. Utgikar, J.P. Scott, Energy forecasting: predictions, reality and analysis of causes of error, Energy Policy 34 (2006) 3087-3092.

DOI: 10.1016/j.enpol.2005.06.006

[18] H. Ceylan, H.K. Öztürk, 2004, Forecasting Energy Consumption of Turkey by ARIMA, Energy Conversion and Management 45(15-16) (2004) 2525-2537.

DOI: 10.1016/j.enconman.2003.11.010

[19] D. Akay, M. Atak, Grey prediction with rolling mechanism for electricity demand forecasting of Turkey, Energy 32 (9) (2007) 1670-1675.

DOI: 10.1016/j.energy.2006.11.014

[20] M.S. Kıran, E. Özceylan, M. Gündüz, T. Paksoy, A novel hybrid approach based on particle swarm optimization and ant colony algorithm to forecast energy demand of Turkey, Energy Conversion and Management 53(1) (2012) 75-83.

DOI: 10.1016/j.enconman.2011.08.004

[21] M.Kankal, E. Uzlu, Neural Network Approach with Teaching–Learning-Based Optimization For Modeling And Forecasting Long-Term Electric Energy Demand in Turkey, Neural Computing and Applications, 28(1) (2017) 737-747.

DOI: 10.1007/s00521-016-2409-2

[22] M.F. Tefek, H.Uğuz, M.Güçyetmez, A new hybrid gravitational search–teaching–learning-based optimization method for energy demand estimation of Turkey, Neural Computing and Applications 31 (2019) 2939–2954.

DOI: 10.1007/s00521-017-3244-9

[23] G.Aydın, Modeling of energy consumption based on economic and demographic factors: The case of Turkey with projections. Renewable and Sustainable Energy Reviews, 35 (7) (2014) 382-389.

DOI: 10.1016/j.rser.2014.04.004

[24] G. Aydın,The development and validation of regression models to predict energy-related CO2 emissions in Turkey. Energy Sources Part B: Economics, Planning, and Policy 10 (2) (2015) 176-182.

DOI: 10.1080/15567249.2013.830662

[25] Z.Yumartacı, E. Aşmaz, 2004 Electric energy demand of Turkey for the year 2050. Energy Sources, 26 (12) (2004) 1157-1164.

DOI: 10.1080/00908310490441520

[26] C. Karaca, H. Karacan, Investigation of factors affecting demand for electricity consumption with multiple regression method, Selçuk University Journal of Engineering, Science and Technology, 4(3) (2016) 182-195.

[27] F.Yüzük, Turkey energy demand forecasting with multiple regression analysis and artificial neural networks. Master thesis, Sivas Cumhuriyet University, Sivas, Turkey (2019).

DOI: 10.5152/turkjnephrol.2020.4300

[28] G.Aydın, The application of trend analysis for coal demand modeling. Energy Sources Part B: Economics, Planning, and Policy 10 (2) (2015) 183-191.

DOI: 10.1080/15567249.2013.813611

[29] G. Aydın, Production modeling in the oil and natural gas industry: An Application of Trend Analysis, Petroleum Science and Technology 32 (5) (2014) 555-564.

DOI: 10.1080/10916466.2013.825271

[30] Y.He, B. Lin,Forecasting China's Total Energy Demand and its Structure Using ADL-MIDAS Model. Energy, 151 (2018) 420-429.

DOI: 10.1016/j.energy.2018.03.067

[31] T. Bayramoğlu, H. Pabuçcu, F.Ç. Boz, Forecasting Primary Energy Demand By Using ANFIS Model for Turkey, Ege Akademik Bakis, 17(3) (2017) 431-445.

[32] M.Kayakuş, The estimation of Turkey's energy demand through ANN and SVR methods. Alphanumeric Journal, 8(2) (2020) 227-235.

[33] S.Özden, A.Öztürk, Electricity energy demand forecasting for an industrial region (Ivedik) by using Artificial Neural Network and Time Series, Bilişim Teknolojileri Journal, 11(3) (2018) 255-26.

[34] Information on https://www.teias.gov.tr.

[35] G.Aydın, The modeling and projection of primary energy consumption by the sources. Energy Sources Part B: Economics, Planning, and Policy 10 (1) (2015) 67-74.

DOI: 10.1080/15567249.2013.771716

[36] W.Zhang, J.Yang, Forecasting natural gas consumption in China by Bayesian model averaging, Energy Reports, 1(1) (2015) 216-220.

DOI: 10.1016/j.egyr.2015.11.001

[37] J. Szoplik, Forecasting of natural gas consumption with artificial neural networks, Energy 85 (5) (2015) 208-220.

DOI: 10.1016/j.energy.2015.03.084

[38] O.F. Demirel, S.Zaim, A.Çalışkan, P. Özuyar, Forecasting natural gas consumption in Istanbul using neural networks and multivariate time series methods, Turkish Journal of Electrical Engineering and Computer Sciences 20 (5) (2012) 695-711.

DOI: 10.3906/elk-1101-1029

[39] Ç. Elmas, Applications of Artificial Intelligence, Artificial Neural Networks - Fuzzy Logic - Genetic Algorithm, Seçkin Publishing, Ankara, (2012).

[40] E. Öztemel, Artificial Neural Networks, Papatya Publishing, İstanbul, (2006).

[41] T.Sağıroğlu, Artificial Intelligence Applications in Engineering I: Artificial Neural Networks, Ufuk Publishing, (2003).