Research Article
BibTex RIS Cite

Transportation Energy Demand Modeling with Artificial Neural Networks

Year 2021, , 2706 - 2715, 15.12.2021
https://doi.org/10.21597/jist.911721

Abstract

Energy demands of countries are changing rapidly in parallel with development, industrialization, urbanization, the spread of technology, prosperity, and population growth. Energy use in the transport sector in the last few years, Turkey has shown a significant increase. Therefore, energy management and predicting are critically important to environmental safety and the upcoming economic well-being. In recent years, studies to determine the energy demand have accelerated. In Addition, in order to estimate the demand levels in the most accurate way, the most appropriate model should be selected. In this study, different models for predicting Turkey's transport energy demand by using artificial neural networks have been established. Population, oil prices, gross domestic product, ton-km, vehicle-km, and passenger-km are selected as parameters by considering 1975 and 2016 data. The best model is tried to be obtained with the models in which different parameters are used together. The best model was established with the oil price, population, ton-km and it was determined that this model had the lowest error and highest R2 values.

References

  • Anonim, 2020a. Dünya Bankası Açık Erişim Veri Merkezi (https://data.worldbank.org/country/turkey?locale=tr).
  • Anonim, 2020b. Dünya Enerji Birliği, Türk Milli Komitesi, Ankara.
  • Anonim, 2020c. Türkiye Karayolları Genel Müdürlüğü, Ankara.
  • Anonim, 2020d. Türkiye İstatistik Kurumu, Ankara.
  • Başkan O, Haldenbilen S, Ceylan H, Ceylan H, 2012. Estimating transport energy demand using ant colony optimization. Energy Sources, Part B: Economics, Planning and Policy, 7(2): 188–199.
  • Ceylan H, Ceylan H, Haldenbilen S, Baskan O, 2008. Transport energy modeling with meta-heuristic harmony search algorithm, an application to Turkey. Energy Policy, 36: 2527–2535.
  • Ceylan Z, Bulkan S, 2018. Türkiye ulaşım kaynaklı enerji ihtiyacının hibrit ANFIS-PSO metodu ile tahmini. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 18: 740-750.
  • Çodur MY, Tortum A, 2015. An artificial neural network model for highway accident prediction: a case study of Erzurum, Turkey. Promet–Traffic&Transportation, 27(3): 217-225.
  • Dhakal S, 2003. Implications of transportation policies on energy and environment in Kathmandu Valley, Nepal. Energy Policy, 31(14): 1493–1507.
  • Forouzanfar M, Doustmohammadi A, Hasanzadeh S, Shakouri GH, 2012. Transport energy demand forecast using multi-level genetic programming. Appl Energy, 91(1): 496–503.
  • Geem WZ, 2011. Transport Energy Demand Modeling of South Korea Using Artificial Neural Network. Energy Policy, 39(8): 4644-4650.
  • Gonzalez PA, Zamarreno JM, 2005. Prediction of hourly energy consumption in buildings based on a feedback artificial neural network. Energy and Buildings, 37(6): 595-601.
  • Haldenbilen S, Ceylan H, 2005. Genetic algorithm approach to estimate transport energy demand in Turkey. Energy Policy, 33(1): 89-98.
  • Haldenbilen S, 2006. Fuel price determination in transportation sector using predicted energy and transport demand. Energy Policy, 34(17): 3078–3086.
  • Hepbasli A, Oturanc G, Kurnaz A, Ergin E, Genc A, Iyit N, 2002. Simple correlations for estimating the energy production of Turkey. Energy Sources, 24(9): 855-867.
  • Hepbasli A, Ozalp N, 2003. Development of energy efficiency and management implementation in the Turkish industrial sector. Energy Convers Manag, 44(2): 231-249.
  • Kalogirou S, Bojic M, 2000. Artificial neural networks for the prediction of the energy consumption of a passive solar building. Energy, 25(5): 479–491.
  • Limanond T, Jomnonkwao S, Srikaew A, 2011. Projection of future transport energy demand of Thailand, Energy Policy, 39(5): 2754-2763.
  • Murat ŞY, Ceylan H, 2006. Use of artificial neural networks for transport energy demand modeling. Energy Policy, 34: 3165-3172.
  • Sahraei MA, Duman H, Çodur MY, Eyduran E, 2021. Prediction of transportation energy demand: Multivariate Adaptive Regression Splines. Energy, 224.
  • Shabbir R, Ahmad SS, 2010. Monitoring urban transport air pollution and energy demand in Rawalpindi and Islamabad using leap model. Energy, 35(5): 2323–2332.
  • Sönmez M, Akgüngör AP, Bektaş S, 2017. Estimating transportation energy demand in Turkey using the artificial bee colony algorithm. Energy, 122: 301–310.
  • Yan X, Crookes RJ, 2009. Reduction potentials of energy demand and GHG emissions in China’s road transport sector. Energy Policy, 37(2): 658–668.
  • Zhang M, Mu H, Li G, Ning Y, 2009. Forecasting the transport energy demand based on PLSR method in China. Energy, 34(9): 1396–1400.

Ulaştırma Enerji Talebinin Yapay Sinir Ağları ile Modellenmesi

Year 2021, , 2706 - 2715, 15.12.2021
https://doi.org/10.21597/jist.911721

Abstract

Ülkelerin enerji talepleri teknolojinin gelişmesi, şehirleşme arzusu, sanayileşme ve sürekli nüfus artışına paralel olarak hızla değişmektedir. Türkiye'de son birkaç yılda ulaştırma sektöründe enerji kullanımı önemli derecede artış göstermiştir. Bu nedenle, enerji yönetimi ve tahmini, çevre güvenliği ve yaklaşan ekonomik refah için kritik önem taşımaktadır. Son yıllarda enerji taleplerinin belirlenmesi çalışmaları hız kazanmıştır. Bununla birlikte talep seviyelerini en doğru şekilde tahmin edebilmek için en uygun modelin seçilmesi gerekmektedir. Bu çalışmada, Yapay Sinir Ağları kullanılarak Türkiye'nin ulaştırma enerji talebini tahmin etmek için farklı modeller kurulmuştur. Yıl, nüfus, yakıt fiyatı, gayri safi yurt içi hasıla, ton-km, araç-km ve yolcu-km olarak belirlenen girdi parametreleri 1975 ve 2019 yılları arasındaki veriler dikkate alınarak seçilmiştir. Parametrelerin farklı kombinasyonlarının kullanıldığı modeller arasından en iyi model elde edilmeye çalışılmıştır. Yakıt fiyatı, nüfus ve ton-km verileri ile en iyi model kurulmuş olup bu modelin en düşük hata ve en yüksek R2 değerlerine sahip olduğu sonucuna ulaşılmıştır.

References

  • Anonim, 2020a. Dünya Bankası Açık Erişim Veri Merkezi (https://data.worldbank.org/country/turkey?locale=tr).
  • Anonim, 2020b. Dünya Enerji Birliği, Türk Milli Komitesi, Ankara.
  • Anonim, 2020c. Türkiye Karayolları Genel Müdürlüğü, Ankara.
  • Anonim, 2020d. Türkiye İstatistik Kurumu, Ankara.
  • Başkan O, Haldenbilen S, Ceylan H, Ceylan H, 2012. Estimating transport energy demand using ant colony optimization. Energy Sources, Part B: Economics, Planning and Policy, 7(2): 188–199.
  • Ceylan H, Ceylan H, Haldenbilen S, Baskan O, 2008. Transport energy modeling with meta-heuristic harmony search algorithm, an application to Turkey. Energy Policy, 36: 2527–2535.
  • Ceylan Z, Bulkan S, 2018. Türkiye ulaşım kaynaklı enerji ihtiyacının hibrit ANFIS-PSO metodu ile tahmini. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 18: 740-750.
  • Çodur MY, Tortum A, 2015. An artificial neural network model for highway accident prediction: a case study of Erzurum, Turkey. Promet–Traffic&Transportation, 27(3): 217-225.
  • Dhakal S, 2003. Implications of transportation policies on energy and environment in Kathmandu Valley, Nepal. Energy Policy, 31(14): 1493–1507.
  • Forouzanfar M, Doustmohammadi A, Hasanzadeh S, Shakouri GH, 2012. Transport energy demand forecast using multi-level genetic programming. Appl Energy, 91(1): 496–503.
  • Geem WZ, 2011. Transport Energy Demand Modeling of South Korea Using Artificial Neural Network. Energy Policy, 39(8): 4644-4650.
  • Gonzalez PA, Zamarreno JM, 2005. Prediction of hourly energy consumption in buildings based on a feedback artificial neural network. Energy and Buildings, 37(6): 595-601.
  • Haldenbilen S, Ceylan H, 2005. Genetic algorithm approach to estimate transport energy demand in Turkey. Energy Policy, 33(1): 89-98.
  • Haldenbilen S, 2006. Fuel price determination in transportation sector using predicted energy and transport demand. Energy Policy, 34(17): 3078–3086.
  • Hepbasli A, Oturanc G, Kurnaz A, Ergin E, Genc A, Iyit N, 2002. Simple correlations for estimating the energy production of Turkey. Energy Sources, 24(9): 855-867.
  • Hepbasli A, Ozalp N, 2003. Development of energy efficiency and management implementation in the Turkish industrial sector. Energy Convers Manag, 44(2): 231-249.
  • Kalogirou S, Bojic M, 2000. Artificial neural networks for the prediction of the energy consumption of a passive solar building. Energy, 25(5): 479–491.
  • Limanond T, Jomnonkwao S, Srikaew A, 2011. Projection of future transport energy demand of Thailand, Energy Policy, 39(5): 2754-2763.
  • Murat ŞY, Ceylan H, 2006. Use of artificial neural networks for transport energy demand modeling. Energy Policy, 34: 3165-3172.
  • Sahraei MA, Duman H, Çodur MY, Eyduran E, 2021. Prediction of transportation energy demand: Multivariate Adaptive Regression Splines. Energy, 224.
  • Shabbir R, Ahmad SS, 2010. Monitoring urban transport air pollution and energy demand in Rawalpindi and Islamabad using leap model. Energy, 35(5): 2323–2332.
  • Sönmez M, Akgüngör AP, Bektaş S, 2017. Estimating transportation energy demand in Turkey using the artificial bee colony algorithm. Energy, 122: 301–310.
  • Yan X, Crookes RJ, 2009. Reduction potentials of energy demand and GHG emissions in China’s road transport sector. Energy Policy, 37(2): 658–668.
  • Zhang M, Mu H, Li G, Ning Y, 2009. Forecasting the transport energy demand based on PLSR method in China. Energy, 34(9): 1396–1400.
There are 24 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Endüstri Mühendisliği / Industrial Engineering
Authors

Merve Kayacı Çodur 0000-0003-1459-9678

Publication Date December 15, 2021
Submission Date April 8, 2021
Acceptance Date July 13, 2021
Published in Issue Year 2021

Cite

APA Çodur, M. K. (2021). Transportation Energy Demand Modeling with Artificial Neural Networks. Journal of the Institute of Science and Technology, 11(4), 2706-2715. https://doi.org/10.21597/jist.911721
AMA Çodur MK. Transportation Energy Demand Modeling with Artificial Neural Networks. Iğdır Üniv. Fen Bil Enst. Der. December 2021;11(4):2706-2715. doi:10.21597/jist.911721
Chicago Çodur, Merve Kayacı. “Transportation Energy Demand Modeling With Artificial Neural Networks”. Journal of the Institute of Science and Technology 11, no. 4 (December 2021): 2706-15. https://doi.org/10.21597/jist.911721.
EndNote Çodur MK (December 1, 2021) Transportation Energy Demand Modeling with Artificial Neural Networks. Journal of the Institute of Science and Technology 11 4 2706–2715.
IEEE M. K. Çodur, “Transportation Energy Demand Modeling with Artificial Neural Networks”, Iğdır Üniv. Fen Bil Enst. Der., vol. 11, no. 4, pp. 2706–2715, 2021, doi: 10.21597/jist.911721.
ISNAD Çodur, Merve Kayacı. “Transportation Energy Demand Modeling With Artificial Neural Networks”. Journal of the Institute of Science and Technology 11/4 (December 2021), 2706-2715. https://doi.org/10.21597/jist.911721.
JAMA Çodur MK. Transportation Energy Demand Modeling with Artificial Neural Networks. Iğdır Üniv. Fen Bil Enst. Der. 2021;11:2706–2715.
MLA Çodur, Merve Kayacı. “Transportation Energy Demand Modeling With Artificial Neural Networks”. Journal of the Institute of Science and Technology, vol. 11, no. 4, 2021, pp. 2706-15, doi:10.21597/jist.911721.
Vancouver Çodur MK. Transportation Energy Demand Modeling with Artificial Neural Networks. Iğdır Üniv. Fen Bil Enst. Der. 2021;11(4):2706-15.