Estimation of Turkey’s Natural Gas Consumption by Machine Learning Techniques

Year 2020, , 120 - 133, 01.03.2020

Osman Emin Erdem Saadettin Erhan Kesen

https://doi.org/10.35378/gujs.586107

Cited By: 4

Abstract

Technological advancements coupled with growing world population require the increasing need of energy. Natural gas is one of the most important usable energy resources. Turkey is with high external dependency on energy as it has its own limited natural and underground energy resources. Thus, in order to effectively and productively use of natural gas purchased from foreign countries and to make reliable and robust energy policies for the years ahead, it is crucial to make a reasonable and plausible prediction for natural gas consumption of Turkey. In this paper, we estimate the natural gas consumption using machine learning techniques on the basis of real monthly data representing natural gas consumption of Turkey between the years 2010 and 2018. The performances of machine learning techniques involving Artificial Neural Networks, Random Forest Tree, Regression, Time Series and Multiple Seasonality Time Series are compared in predicting the natural gas consumption of Turkey. Experimental results show that among the five techniques, artificial neural networks produce the best estimation, having the lowest mean square errors, followed by regression method. Time series shows the worst performance among all the techniques.

Keywords

Energy consumption, Natural gas, Estimation, Machine Learning, R language

References

• 1. T.C. Enerji ve Tabii Kaynaklar Bakanlığı https://www.enerji.gov.tr/tr-TR/Sayfalar/Dogal-Gaz Publish date April 18, 2019. Data accessed May 15, 2019.
• 2. Bayrac, H.N., “The Economic Structure of International Natural Gas Market and Applied Policies”, Eskişehir Osmangazi Üniversitesi İİBF Dergisi, 13 (3): 13-36, (2018).
• 3. Bayrac, H.N., “The Economic Structure of International Natural Gas Market and Applied Policies”, Eskişehir Osmangazi Üniversitesi İİBF Dergisi, 13 (3): 13-36, (2018).
• 4. Brett, L., Machine Learning with R Second Edition, Packt Publishing, Birmingham, (2015).
• 5. Es, H.A., Hamzaçebi, C., “Forecasting The Net Energy Demand Of Turkey By Artificial Neural Networks”, J. Fac. Eng. and Arc. Gazi Univ., 29 (3): 495-504, (2014).
• 6. Karaca, C., Karacan, H., “Investigation Of Factors Affecting Demand For Electricity Consumption With Multiple Regression Method”, SUJEST, 4 (3): 183-195, (2016).
• 7. Hamzaçebi, C., Kutay, F., “Electrıc Consumption Forecasting of Turkey Using Artifial Neural Networks Up To Year 2010”, J. Fac. Eng. and Arch. Gazi Univ., 19 (3): 227-233, (2004).
• 8. Şenol, Ü., Musayev, Z., “Estimating Wind Energy Potential by Artificial Neural Networks Method”, Bilge International Journal of Science and Technology Research, 1(1): 23-31, (2017).
• 9. Makas, Y., Karaatlı, M., “Multi-Period Estimation Of Hydroelectric Power Generation With Artificial Neural Network”, The Journal of Faculty of Economics and Administrative Sciences, 21 (3): 757-772, (2016).
• 10. Aksoy, S.A., Eryiğit, E., Hashimova, N., İşbilir, M., Avşar, Z.M. and Köksal, G., A “Prediction And Bidding System Design For Wind Power Generation”, Endüstri Mühendisliği Dergisi, 24 (3-4): 4-15, (2013).
• 11. Çoban, O., Özcan, C.C., “Sektörel Açıdan Enerjinin Artan Önemi: Konya İli İçin Bir Doğalgaz Talep Tahmini Denemesi”, SÜ İİBF Sosyal ve Ekonomik Araştırmalar Dergisi, 11 (22): 85-106, (2011).
• 12. Dündar, C., Oğuz, K., Dokuyucu, K. and Bacanlı, H.,”Kısa Süreli Rüzgar Enerjisi Tahmini”, VI. Yeni ve Yenilenebilir Enerji Kaynakları Sempozyumu, Kayseri, 2-12, (2011).
• 13. Yavuzdemir, M., “Türkiye'nin Kısa Dönem Yıllık Brüt Elektrik Enerjisi Talep Tahmini”, MSc. Thesis, Ankara Üniversitesi Sosyal Bilimler Enstitüsü İşletme Anabilim Dalı, Ankara, (2014).
• 14. Eren, T., “Grey Forecasting Method In Natural Gas Consumption Planning And Turkey Implementation”, MSc. Thesis, İstanbul Ticaret University, Institute of Science and Technology, İstanbul, (2017).
• 15. Bianco, V., Manca, O., Nardini, S., “Electricity consumption forecasting in Italy using linear regression models”, Energy, 34 (9): 1413–1421, (2009).
• 16. Al-Fattah, S.M., “Time Series Modeling for U.S. Natural Gas Forecasting”, International Petroleum Technology Conference, Doha-Qatar, (2005).
• 17. Demirel, Ö.F., Zaim, S., Çalışkan, A. and Özuyar P., “Forecasting Natural Gas Consumption in İstanbul Using Neural Networks And Multivariate Time Series Methods”, Turkısh Journal Of Electrıcal Engıneerıng Computer Scıences, 20 (5): 695-711, (2012).
• 18. Busse, S., Halmholz P. and Weinmann M., “Forecasting Day Ahead Spot Price Movements Of Natural Gas – An Analysis Of Potential Influence Factors On Basis Of A NARX Neural Network”, Multikonferenz Wirtschaftsinformatik, 13(1): 1395 - 1406, (2012).
• 19. Vıtullo, S.R., Brown, R.H., Corlıss, G.F. and Marx, B.M., “Mathematical Models For Natural Gas Forecasting”, Canadian Applied Mathematics Quarterly, 17 (4): 807-827, (2009).
• 20. Brett, L., Machine Learning with R Second Edition, Packt Publishing, Birmingham, (2015).
• 21. Cutler, A., Stevens J.R., Cutler D.R., Ensemble Machine Learning: Methods and Applications, Springer, (eds.) Zhang, C., Ma, Y., New York, (2012).
• 22. Toomey, J.W., “MRP II Planning for Manufacturing Excellence”, Hardbaound, New York, (1996).
• 23. Sandy, R., “Statistics for Business and Economics”, Mc-Graw Hill Higher Education, C.USA,(1990).
• 24. De Livera, A.M., Hyndman, R.J. and Snyder, R.D., “Forecasting time series with complex seasonal patterns using exponential smoothing”, Journal of the American Statistical Association, 15(9): 2-39, (2010).