Doğal Gaz Talep Tahmininin Yapay Sinir Ağları İle Modellenmesi: Danimarka Örneği

Abstract

Küresel enerji yapısındaki tarihsel izlek, özellikle doğal gaz ve yenilenebilir enerji talebinin arttığı bilgisini sunmaktadır. Bu kapsamda doğal gaz, en önemli enerji kaynaklarındandır birisidir ve yüksek metan içeriği ile karakterize edildiğinden, yenilenebilir enerjiden sonraki en temiz enerji kaynağı kabul edilmektedir. Aynı zamanda, küresel ısınmanın azaltılması ve iklim değişikliği sorunsalına çözüm için gerekli olan düşük karbonlu enerji sistemlerine geçişte çok önemli bir köprü yakıtı olarak değerlendirilmektedir. Bu bağlamda, dünyanın sürdürülemez olduğu bir gelecek öngörüsünde, enerji kaynaklarının öncülüğünde bir dizi politika önleminin alınması gerekmektedir. Bununla birlikte, bu politika önlemlerinin ülkelerin enerji politikalarındaki toplumsal davranış ve tercihlerdeki değişimlerle güçlendirilmesi gerekmektedir. Dolayısıyla, artış trendinde olan doğal gaz enerji kaynağı ile ilgili politika kararlarının alınmasında ve uygulanmasında doğal gaz talep tahmin işlemleri oldukça önemli bir yere sahiptir. Bu kapsamda çalışmanın amacı, Danimarka’nın 2021-2050 dönem aralığındaki yıllık doğal gaz talebinin Yapay Sinir Ağları metodolojisi izlenerek tahmin edilmesidir. Amaç doğrultusunda 1984-2020 dönem aralığına ait doğal gaz tüketimi, doğal gaz üretimi, doğal gaz ithalatı, GSYH, nüfus ve enflasyon değişkenlerine ilişkin veriler kullanılmıştır. Ampirik kanıtlarda, modelin ortalama mutlak yüzde hatasının 2.22 düşük bir hata oranına sahip güçlü, kararlı ve etkili bir yöntem olduğu görülmüştür. Bununla birlikte, senaryo tahmin sonuçları doğal gaz talebinin 2050 yılında 2.25 milyar m3 tüketime ulaşacağını göstermiştir.

Keywords

• Doğal Gaz Talebi
• Tahmin
• Yapay Sinir Ağları
• Danimarka

Modeling of Natural Gas Demand Forecast with Artificial Neural Networks: The Example of Denmark

Abstract

The historical trajectory in the global energy structure presents the information that especially demand for natural gas and renewable energy is increasing. In this context, natural gas is one of the most important energy sources and is considered the cleanest energy source after renewable energy, as it is characterized by its high methane content (70-90%). At the same time, it is considered as a very important bridge fuel in the transition to low-carbon energy systems, which is necessary for reducing global warming and solving the problem of climate change. In this context, in the foresight of a future in which the world is unsustainable, a series of policy measures should be taken under the leadership of energy resources. At the same time, these policy measures need to be strengthened by changes in the social behavior and preferences of countries’ energy policies. Therefore, natural gas demand forecasting processes have a very important place in taking and implementing policy decisions regarding the natural gas energy source, which is in an increasing trend. In this context, the aim of the study is to estimate the annual natural gas demand of Denmark in the 2021-2050 period by following the Artificial Neural Networks methodology. For the purpose, data on natural gas consumption, natural gas production, natural gas imports, GDP, population and inflation variables for the 1984-2020 period were used. In the empirical evidence, the mean absolute percent error of the model has been shown to be a powerful, stable and effective method with a low error rate of 2.22. At the same time, scenario estimation results showed that natural gas demand will reach 2.25 billion m3 consumption in 2050.

Keywords

• Natural Gas Demand
• Forecast
• Artificial Neural Networks
• Denmark

References

1. Akpinar, M., Adak, F. M., & Yumusak, N. (2017). Day-ahead natural gas demand forecasting using optimized ABC_based neural network with sliding window technique: The case study of regional basis in Turkey. Energies, 10(781), 1-20.
2. Akpinar, M., & Yumusak, N. (2016). Year ahead demand forecast of city natural gas using seasonal time series methods. Energies, 9(727), 1-17.
3. Bai, Y., & Li, C. (2016). Daily natural gas consumption forecasting based on a structure-calibrated support vector regression approach. Energy and Buildings, 127, 571-579.
4. Bakay, M. S., & Ağbulut, Ü. (2021). Electricity production based forecasting of greenhouse gas emissions in Turkey with deep learning, support vector machine and artificial neural network algorithms. Journal of Cleaner Production, 285, 1-18.
5. Bojesen, M., Skov-Petersen, H., & Gylling M. (2015). Forecasting the potential of Danish biogas production - Spatial representation of Markov chains. Biomass and Bioenergy, 81, 462-472.
6. BP, British Petroleum. (2020). Energy Outlook: 2020 edition, 1-157.
7. BP, British Petroleum. (2021). Statistical Review of World Energy 70th edition, 1-69. BP, British Petroleum. (2021). https://www.bp.com/en/global/corporate/energy-economics/statistical-review-of-world-energy.html (erişim tarihi: 21.09.2021).
8. Chai, J., Liang, T., Lai, K. K., Zhang, Z. G., & Wang, S. (2018). The future natural gas consumption in China: Based on the LMDI-STIRPAT-PLSR framework and scenario analysis. Energy Policy, 119, 215-225.

9. Denmark Statistical Office. (2021). https://www.dst.dk/en/Statistik/emner/miljoe-og-energi (erişim tarihi: 04.09.2021).
10. Ervural, B. C., Beyca, O. F., & Zaim, S. (2016). Model estimation of ARMA using genetic algorithms: A case study of forecasting natural gas consumption. Procedia-Social and Behavioral Sciences, 235, 537-545.
11. Gascón, A., & Sanchéz-Úbeda, E. F. (2018). Automatic specification of piecewise linear additive models: application to forecasting of natural gas demand. Statistics and Computing, 28(1), 201-217.
12. Hagos, D. A., & Ahlgren, E. O. (2020). Exploring cost-effective transitions to fossil independent transportation in the future energy system of Denmark. Applied Energy, 261, 1-20.
13. Hosovský, A., Pitel, J., Adámek, M., Mizáková, J., & Zidek K. (2021). Comparative study of week-ahead forecasting of daily gas consumption in buildings using regression ARMA/SARMA and genetic-algorithm-optimized regression wavelet neural network models. Journal of Building Engineering, 34, 1-20.
14. Hribar, R., Potocnik, P., Silc, J., & Papa, G. (2019). A comparison of models for forecasting the residential natural gas demand of an urban area. Energy, 167, 511-522.
15. Hubbert, M. K. (1949). Energy from fossil fuels. Science, 109(2823), 103-109.
16. Hubbert, M. K. (1956). Nuclear energy and the fossil fuel. Drilling and Production Practice, American Petroleum Institute, New York, USA.
17. Jiang, P., Yang, H., Li, H., & Wang Y. (2021). A developed hybrid forecasting system for energy consumption structure forecasting based on fuzzy time series and information granularity. Energy, 219, 1-14.
18. Karabiber, O. A., & Xydis, G. (2019). Electricity Price Forecasting in the Danish Day-Ahead Market Using the TBATS, ANN and ARIMA Methods. Energies, 12(928), 1-29.
19. Karabiber, O. A., & Xydis, G. (2020). Forecasting day-ahead natural gas demand in Denmark. Journal of Natural Gas Science and Engineering, 76, 1-25.
20. Karabiber, O. A., & Xydis, G. (2021). A review of the day-ahead natural gas consumption in Denmark: starting point towards forecasting accuracy improvement. International Journal of Coal Science & Technology, 8(1), 1-22.
21. Karimi, H., & Dastranj, J. (2014). Artificial neural network-based genetic algorithm to predict natural gas consumption. Energy Systems, 5(3), 571-581.
22. Liu, G., Dong, X., Jiang, Q., Dong, C., & Li, J. (2018). Natural gas consumption of urban households in china and corresponding influencing factors. Energy Policy, 122, 17-26.
23. Liu, J., Wang, S., Wei, N., Chen, X., Xie, H., & Wang, J. (2021). Natural gas consumption forecasting: A discussion on forecasting history and future challenges. Journal of Natural Gas Science and Engineering, 90, 1-20.
24. Lu, H., Azimi, M., & Iseley, T. (2019). Short-term load forecasting of urban gas using a hybrid model based on improved fruit fly optimization algorithm and support vector machine. Energy Reports, 5, 666-677.
25. Marziali, A., Fabbiani, E., & Nicolao, G. D. (2019). Short-term Forecasting of Italian Residential Gas Demand. Computer Science, Mathematics, https://arxiv.org/pdf/1902.00097v1.pdf, 1-17.
26. McKenna, R., D’Andrea, M., & González M. G. (2021). Analysing long-term opportunities for offshore energy system integration in the Danish North Sea. Advances in Applied Energy, 4, 1-16.
27. Meibom, P., Hilger, K. B., Madsen, H., Vinther, D., & Vinther D. (2013). Energy Comes Together in Denmark: The Key to a Future Fossil-Free Danish Power System. IEEE Power and Energy Magazine, 11(5), 46-55.
28. Merkel, G. D., Povinelli, R. J., & Brown, R. H. (2018). Short-term load forecasting of natural gas with deep neural network regression. Energies, 11(2008): 1-12.
29. Ogliari, E., Guilizzoni , M., Giglio, A., & Pretto S. (2021). Wind power 24-h ahead forecast by an artificial neural network and an hybrid model: Comparison of the predictive performance. Renewable Energy, 178, 1466-1474.
30. Oliver, R., Duffy, A., Enright, B., & O’Connor R. (2017). Forecasting peak-day consumption for year-ahead management of natural gas networks. Utilities Policy, 44, 1-11.
31. Özmen, A., Yılmaz, Y., & Weber, G.-W. (2018). Natural gas consumption forecast with MARS and CMARS models for residential users. Energy Economics, 70, 357-381.
32. Panapakidis, I. P., & Dagoumas, A. S. (2017). Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model. Energy, 118, 231-245.
33. Pata, U. K. (2021). Linking renewable energy, globalization, agriculture, CO2 emissions and ecological footprint in BRIC countries: A sustainability perspective. Renewable Energy, 173, 197-208.
34. Peng, S., Chen, R., Yu, B., Xiang, M., Lin, X., & Liu, E. (2021). Daily natural gas load forecasting based on the combination of long short term memory, local mean decomposition, and wavelet threshold denoising algorithm. Journal of Natural Gas Science and Engineering, 95, 1-10.
35. Pino-Mejías, R., Fargallo, A. P, Rubio-Bellido, C., & Arcas, J. A. P. (2017). Comparison of linear regression and artificial neural networks models to predict heating and cooling energy demand, energy consumption and CO2 emissions. Energy, 118, 24-36.
36. Pinson, P., Mitridati, L., Ordoudis, C., & Østergaard, J. (2017). Towards Fully Renewable Energy Systems: Experience and Trends in Denmark. CSEE Journal of Power and Energy Systems, 3(1), 26-35.
37. Sällh, D., Höök, M., Grandell, L., & Davidsson, S. (2014). Evaluation and update of Norwegian and Danish oil production forecasts and implications for Swedish oil import. Enegy, 65, 333-345.
38. Sen, D., Günay, M. E., & Tunç, K. M. M. (2019). Forecasting annual natural gas consumption using socio-economic indicators for making future policies. Energy, 173, 1106-1118.
39. Sharma, V., Cali, Ü., Sardana, B., Kuzlu, M., Banga, D., & Pipattanasomporn, M. (2021). Data-driven short-term natural gas demand forecasting with machine learning techniques. Journal of Petroleum Science and Engineering, 206, 1-12.
40. Shaikh, F., & Ji, Q. (2016). Forecasting natural gas demand in China: Logistic modelling analysis. International Journal of Electrical Power & Energy Systems, 77, 25-32.
41. Soini, V. (2021). Wind power intermittency and the balancing power market: Evidence from Denmark. Energy Economics, 100, 1-11.
42. Soldo, B., Potocnik, P., Simunovic, G., Saric, T., & Govekar, E. (2014). Improving the residential natural gas consumption forecasting models by using solar radiation. Energy and Buildings, 69, 498-506.
43. Stephenson, E., Doukas, A., & Shaw, K. (2012). Greenwashing gas: Might a ‘transition fuel’ label legitimize carbon-intensive natural gas development? Energy Policy, 46, 452-459.
44. Szoplik, J. (2015). Forecasting of natural gas consumption with artificial neural networks. Energy, 85, 208-220.
45. Taşpınar, F., Çelebi, N., & Tutkun, N. (2013). Forecasting of daily natural gas consumption on regional basis in Turkey using various computational methods. Energy and Buildings, 56, 23-31.
46. Tschopp, D., Tian, Z., Berberich, M., Fan, J., Perers, B., & Furbo, S. (2020). Large-scale solar thermal systems in leading countries: A review and comparative study of Denmark, China, Germany and Austria. Applied Energy, 270, 1-19.
47. Ülkü, H., & Yalpır, Ş. (2021). Enerji talep tahmini için metodoloji geliştirme: 2030 yılı Türkiye örneği. NÖHÜ Mühendislik Bilimleri Dergisi, 10(1): 188-201.
48. Veenman, S., Sperling, K., & Hvelplund, F. (2019). How future frames materialize and consolidate: The energy transition in Denmark. Futures, 114, 1-10.
49. Wadud, Z., Dey, H. S., Kabir, M. A., & Shahidul, I. K. (2011). Modeling and forecasting natural gas demand in Bangladesh. Energy Policy, 39(11), 7372-7380.
50. Wang, D., Liu, Y., Wu, Z., Fu, H., Shi, Y., & Guo, H. (2018). Scenario analysis of natural gas consumption in China based on wavelet neural network optimized by particle swarm optimization algorithm. Energies, 11(825), 1-16.
51. Wang, J., & Li, N. (2020). Influencing factors and future trends of natural gas demand in the eastern, central and western areas of China based on the grey model. Natural Gas Industry B 7, 2020, 473-483.
52. Wang, Y., Zou, R., Liu, F., Zhang, L., & Liu, Q. (2021). A review of wind speed and wind power forecasting with deep neural networks. Applied Energy, 304, 1-24.
53. Wei, N., Li, C., Peng, X., Li, Y., & Zeng, F. (2019). Daily natural gas consumption forecasting via the application of a novel hybrid model. Applied Energy, 250, 358-368.
54. World Bank. (2021). https://databank.worldbank.org/indicator/NY.GDP.MKTP.KD.ZG/1ff4a498/Popular-Indicators (erişim tarihi: 04.09.2021).
55. Wu, Y.-H., & Shen, H. (2018) Grey-related least squares support vector machine optimization model and its application in predicting natural gas consumption demand. Journal of Computational and Applied Mathematics, 338, 212-220.
56. Ye, J., Dang, Y., Ding, S., & Yang, Y. (2019). A novel energy consumption forecasting model combining an optimized DGM (1, 1) model with interval grey numbers. Journal of Cleaner Production, 229, 256-267.
57. Zheng, C., Wu, W.-Z., Jiang, J., & Li, Q. (2020). Forecasting Natural Gas Consumption of China Using a Novel Grey Model. Wiley Hindawi Complexity, 2020, 1-9.