Comparative analysis of metaheuristic optimization algorithms for natural gas demand forecast with meteorological parameters

Öz

Natural gas demand forecasting is of great importance especially for decision-makers of national economies with high energy consumption, the industrial sector, and all players in the natural gas market, in particular. This study aims to present Turkey's monthly natural gas demand forecast model according to meteorological parameters. In the study, models were created with four current metaheuristic algorithms of Artificial Bee Colony Algorithm (ABC), Charged System Search Algorithm (CSS), Crow Search Algorithm (CSA), and Harmony Search Algorithm (HSA) were compared. In the research, three mathematical models, linear, exponential, and quadratic, were developed and the performances of the models were evaluated with six different global error measurement metrics (AE, MAE, R2, MAPE, RMS, MARNE). In the study, average temperature, pressure, humidity, wind, and precipitation meteorological data were used as input parameters. The data between 2010-2017 was applied as training data, and the data between 2018-2020 was applied as test data. The most successful forecasting model for the natural gas demand forecast training data set is the quadratic model of the CSS algorithm, while the most successful forecasting model for the test data is the quadratic model of the ABC algorithm.

Anahtar Kelimeler

• Natural gas demand forecast
• Forecast according to meteorological parameters
• Metaheuristic algorithms.

Meteorolojik parametreler ile doğal gaz talep tahmini için metasezgisel optimizasyon algoritmalarının karşılaştırmalı analizi

Öz

Doğal gaz talep tahmini, özellikle enerji tüketimi yüksek ülke ekonomilerinin karar vericileri, sanayi sektörü ve doğal gaz piyasasındaki tüm oyuncular için büyük önem taşımaktadır. Bu çalışma, meteorolojik parametrelere göre Türkiye'nin aylık doğal gaz talep tahmini modelini sunmayı amaçlamaktadır. Çalışmada Yapay Arı Kolonisi Algoritması (ABC), Yüklü Sistem Arama Algoritması (CSS), Karga Arama Algoritması (CSA) ve Harmoni Arama Algoritması (HSA) dört güncel metasezgisel algoritma ile oluşturulan modeller karşılaştırılmıştır. Araştırmada lineer, üstel (exponential) ve ikinci dereceden (quadratic) olmak üzere üç matematiksel model geliştirilmiş ve modellerin performansları altı farklı global hata ölçüm metrikleri (AE, MAE, R2, MAPE, RMS, MARNE) ile değerlendirilmiştir. Çalışmada ortalama sıcaklık, basınç, nem, rüzgar ve yağış meteorolojik veriler girdi parametreleri olarak kullanılmıştır. 2010-2017 yılları arasındaki veriler eğitim verileri, 2018-2020 yılları arasındaki veriler ise test verisi olarak uygulanmıştır. Doğal gaz talep tahmini eğitim veri seti için en başarılı tahmin eden model CSS algoritmasının quadratic modeliyken, test verilerinde ise en başarılı tahmin ABC algoritmasının quadratic modelidir.

Anahtar Kelimeler

• Doğal gaz talep tahmini
• Meteorolojik parametrelere göre tahmin
• Metasezgisel algoritmalar.

Kaynakça

1. D. Pavlović, E. Banovac, and N. Vištica, “Defining a composite index for measuring natural gas supply security-The Croatian gas market case,” Energy Policy, vol. 114, pp. 30–38, 2018.
2. N. Abas, A. Kalair, and N. Khan, “Review of fossil fuels and future energy technologies,” Futures, vol. 69, pp. 31–49, 2015.
3. C. by fuel type-Exajoules and C. D. Emissions, “bp Statistical Review of World Energy June 2020,” 2006.
4. World Energy Council, “Türkiye enerji piyasaları araştırma raporu,” 2018. [Online]. Available: https://www.dunyaenerji.org.tr/wp-content/uploads/2018/07/TEPG1.pdf.
5. L. Montuori and M. Alcázar-Ortega, “Demand response strategies for the balancing of natural gas systems: Application to a local network located in The Marches (Italy),” Energy, vol. 225, p. 120293, 2021.
6. G. E. Doğan, “Karadeniz Bölgesinde Boru Hatları Jeopolitiği,” Karadeniz Araştırmaları, no. 57, pp. 17–31, 2018.
7. Z. Dubský, L. Tichý, and D. Pavliňák, “A quantifiable approach to the selection of criteria and indexation for comparison of the gas pipeline projects leading to the EU: diversification rationality against securitisation?,” Energy, p. 120238, 2021.
8. B. Kaynak, “From Blue Stream To Turkish Stream An Assessment Of Turkey’s Energy Dependence On Russia,” Aurum J. Soc. Sci., vol. 3, no. 1, pp. 79–90, 2018.

9. Türkiye İstatistik Kurumu, “Enerji Kaynaklarına Göre Elektrik Enerjisi Üretimi ve Payları,” 2021. https://data.tuik.gov.tr/Kategori/GetKategori?p=cevre-ve-enerji-103&dil=1 (accessed Sep. 22, 2021).
10. EPDK, “Elektrik piyasası 2018 yılı piyasa gelişim raporu,” 2018.
11. Worldbank, “Supporting countries in unprecedented times,” 2020.
12. EPDK, “Doğal Gaz Piyasası 2020 Yılı Sektör Raporu,” 2020.
13. Gazbir, “2017 Yılı Doğal Gaz Dağıtım Sektörü Raporu,” Anakara, 2017.
14. E. Erdogdu, “Natural gas demand in Turkey,” Appl. Energy, vol. 87, no. 1, pp. 211–219, 2010.
15. F. Asche, O. B. Nilsen, and R. Tveteras, “Natural gas demand in the European household sector,” Energy J., vol. 29, no. 3, 2008.
16. F. Shaikh and Q. Ji, “Forecasting natural gas demand in China: Logistic modelling analysis,” Int. J. Electr. Power Energy Syst., vol. 77, pp. 25–32, 2016.
17. Y. Karadede, G. Ozdemir, and E. Aydemir, “Breeder hybrid algorithm approach for natural gas demand forecasting model,” Energy, vol. 141, pp. 1269–1284, 2017.
18. I. P. Panapakidis and A. S. Dagoumas, “Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model,” Energy, vol. 118, pp. 231–245, 2017.
19. Y.-H. Wu and H. Shen, “Grey-related least squares support vector machine optimization model and its application in predicting natural gas consumption demand,” J. Comput. Appl. Math., vol. 338, pp. 212–220, 2018.
20. H. Su, E. Zio, J. Zhang, M. Xu, X. Li, and Z. Zhang, “A hybrid hourly natural gas demand forecasting method based on the integration of wavelet transform and enhanced Deep-RNN model,” Energy, vol. 178, pp. 585–597, 2019.
21. V. Bianco, F. Scarpa, and L. A. Tagliafico, “Scenario analysis of nonresidential natural gas consumption in Italy,” Appl. Energy, vol. 113, pp. 392–403, 2014.
22. R. Oliver, A. Duffy, B. Enright, and R. O’Connor, “Forecasting peak-day consumption for year-ahead management of natural gas networks,” Util. Policy, vol. 44, pp. 1–11, 2017.
23. F. Taşpınar, N. Celebi, and N. Tutkun, “Forecasting of daily natural gas consumption on regional basis in Turkey using various computational methods,” Energy Build., vol. 56, pp. 23–31, 2013.
24. J. Szoplik, “Forecasting of natural gas consumption with artificial neural networks,” Energy, vol. 85, pp. 208–220, 2015.
25. O. F. Beyca, B. C. Ervural, E. Tatoglu, P. G. Ozuyar, and S. Zaim, “Using machine learning tools for forecasting natural gas consumption in the province of Istanbul,” Energy Econ., vol. 80, pp. 937–949, 2019.
26. P. Potočnik, J. Šilc, and G. Papa, “A comparison of models for forecasting the residential natural gas demand of an urban area,” Energy, vol. 167, pp. 511–522, 2019.
27. O. A. Karabiber and G. Xydis, “Forecasting day-ahead natural gas demand in Denmark,” J. Nat. Gas Sci. Eng., vol. 76, p. 103193, 2020.
28. L. Zhu, M. S. Li, Q. H. Wu, and L. Jiang, “Short-term natural gas demand prediction based on support vector regression with false neighbours filtered,” Energy, vol. 80, pp. 428–436, 2015.
29. C. Rui, W. Jian, W. Li, Y. Ningjie, and Z. Pengyan, “The forecasting of China natural gas consumption based on genetic algorithm,” in 2009 Fifth International Joint Conference on INC, IMS and IDC, 2009, pp. 1436–1439.
30. H. Ma and Y. Wu, “Grey predictive on natural gas consumption and production in China,” in 2009 Second Pacific-Asia Conference on Web Mining and Web-based Application, 2009, pp. 91–94.
31. X. Wan, Q. Zhang, and G. Dai, “Research on forecasting method of natural gas demand based on GM (1, 1) model and Markov chain,” in 2014 IEEE 13th International Conference on Cognitive Informatics and Cognitive Computing, 2014, pp. 436–441.
32. M. D. Z. Rahman, M. D. N. Sajib, M. M. S. H. Rifat, M. Hossam-E-Haider, and M. A. A. Khan, “Forecasting the long term energy demand of Bangladesh using SPSS from 2011–2040,” in 2016 3rd International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2016, pp. 1–5.
33. R. H. Brown, S. R. Vitullo, G. F. Corliss, M. Adya, P. E. Kaefer, and R. J. Povinelli, “Detrending daily natural gas consumption series to improve short-term forecasts,” in 2015 IEEE Power & Energy Society General Meeting, 2015, pp. 1–5.
34. H. Khani and H. E. Z. Farag, “An online-calibrated time series based model for day-ahead natural gas demand forecasting,” IEEE Trans. Ind. Informatics, vol. 15, no. 4, pp. 2112–2123, 2018.
35. W. Qiao, Z. Yang, Z. Kang, and Z. Pan, “Short-term natural gas consumption prediction based on Volterra adaptive filter and improved whale optimization algorithm,” Eng. Appl. Artif. Intell., vol. 87, p. 103323, 2020.
36. C. Liu, W.-Z. Wu, W. Xie, T. Zhang, and J. Zhang, “Forecasting natural gas consumption of China by using a novel fractional grey model with time power term,” Energy Reports, vol. 7, pp. 788–797, 2021.
37. M. AKPİNAR and N. Yumuşak, “Günlük temelli orta vadeli şehir doğal gaz talebinin tek değişkenli istatistik teknikleri ile tahmini,” Gazi Üniversitesi Mühendislik Mimar. Fakültesi Derg., vol. 35, no. 2, pp. 725–742, 2020.
38. C. Zheng, W.-Z. Wu, W. Xie, and Q. Li, “A MFO-based conformable fractional nonhomogeneous grey Bernoulli model for natural gas production and consumption forecasting,” Appl. Soft Comput., vol. 99, p. 106891.
39. A. S. Anđelković and D. Bajatović, “Integration of weather forecast and artificial intelligence for a short-term city-scale natural gas consumption prediction,” J. Clean. Prod., vol. 266, p. 122096, 2020.
40. L. Sun, M. Koopialipoor, D. Jahed Armaghani, R. Tarinejad, and M. M. Tahir, “Applying a meta-heuristic algorithm to predict and optimize compressive strength of concrete samples,” Eng. Comput., vol. 37, no. 2, pp. 1133–1145, 2021.
41. D. Karaboga, “An idea based on honey bee swarm for numerical optimization,” Citeseer, 2005.
42. A. Kaveh and S. Talatahari, “A novel heuristic optimization method: charged system search,” Acta Mech., vol. 213, no. 3, pp. 267–289, 2010.
43. [43] A. Askarzadeh, “A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm,” Comput. Struct., vol. 169, pp. 1–12, 2016.
44. [44] K. S. Lee and Z. W. Geem, “A new structural optimization method based on the harmony search algorithm,” Comput. Struct., vol. 82, no. 9–10, pp. 781–798, 2004.
45. [45] D. Manjarres et al., “A survey on applications of the harmony search algorithm,” Eng. Appl. Artif. Intell., vol. 26, no. 8, pp. 1818–1831, 2013.
46. [46] A. Kaveh and S. Talatahari, “A hybrid CSS and PSO algorithm for optimal design of structures,” Struct. Eng. Mech., vol. 42, no. 6, pp. 783–797, 2012.
47. [47] D. Karaboga and B. Akay, “Artificial bee colony (ABC) algorithm on training artificial neural networks,” in 2007 IEEE 15th Signal Processing and Communications Applications, 2007, pp. 1–4.
48. [48] S. Das, A. Biswas, S. Dasgupta, and A. Abraham, “Bacterial foraging optimization algorithm: theoretical foundations, analysis, and applications,” in Foundations of computational intelligence volume 3, Springer, 2009, pp. 23–55.