Intelligent prediction of gas consumption in three-hour intervals, using data recorded in specific time periods

Document Type : Original Article

Authors
Iman Mohammadi 1
Mohsen Taghavi 2
1 Ph.D. in Mechanical Engineering, Khorasan Razavi Gas Company, Mashhad, Iran
2 B.Sc. in Chemical Engineering, Khorasan Razavi Gas Company, Mashhad, Iran
Abstract
Gas consumption, as one of the most consumed energy carriers in the country, is very important in crisis management, production management, allocation and consumption, preventing wastage and reducing environmental pollution. However, due to the oldness of the measuring equipment, it is not possible to record data continuously, and the available information about gas consumption is usually limited to the periodic gas consumption reports of consumers. Therefore, real-time forecasting of gas consumption is associated with high uncertainty, and it is not possible to check the accuracy of the forecast due to the lack of real-time data. The aim of this research is to intelligently predict gas consumption in three-hour intervals based on its periodic consumption information. The method presented in this research includes three steps.In the first step, using the fuzzy clustering algorithm, the gas consumption data of household consumers are divided into three categories: low consumption, balanced and high consumption. In the second step, using a deep neural network, the temperature is predicted in three-hour intervals. In the third step, using a system based on fuzzy logic, the three-hour gas consumption of household consumers is estimated based on the predicted temperature, day of the year and time of day. The implementation of the proposed method on the data of the city of Birjand shows that the total instantaneous consumption predicted for all three low-consumption, balanced and high-consumption clusters follows the average periodic consumption of the consumers of those clusters with an acceptable error. Also, the presence of a strong negative correlation between temperature and gas consumption, especially for balanced consumers in cold seasons, confirms the influence of gas consumption on temperature.

Keywords

Subjects

  1. Namazkhan, C. Albers, and L. Steg, “A decision tree method for explaining household gas consumption, The role of building characteristics, socio-demographic variables, psychological factors and household behaviour,” Renew. Sustain. Energy Rev. 119, (2019), p 109542.
  2. Karimi and J. Dastranj, “Artificial neural network-based genetic algorithm to predict natural gas consumption,” Energy Syst. 5, no. 3, (2014), p 571–581.
  3. Ferreira MA, Marco AR, Lee HK. "Multiscale modeling: a Bayesian perspective." Springer Science Business Media, (2007).
  4. Humeau-Heurtier, Anne. "The multiscale entropy algorithm and its variants: A review." Entropy 17, no. 5, (2015), p 3110-3123.
  5. Costa, M; Goldberger, A.L.; Peng, C.K. Multiscale entropy analysis of complex physiologic time series. Phys. Rev. Lett. 2002, 89, 068102.
  6. Costa, M; Goldberger, A.L.; Peng, C.K. Multiscale entropy analysis of biological signals. Phys. Rev. E 2005, 71, 021906.
  7. Valencia, J.F.; Porta, A.; Vallverdu, M.; Claria, F.; Baranowski, R.; Orlowska-Baranowska, E.; Caminal, P. Refined multiscale entropy: Application to 24-h Holter recordings of heart period variability in healthy and aortic stenosis subjects. IEEE Trans. Biomed. Eng. 2009, 56, 2202–2213.
  8. Wu, S.D.; Wu, C.W.; Lin, S.G.; Lee, K.Y.; Peng, C.K. Analysis of complex time series using refined composite multiscale entropy. Phys. Lett. A 2014, 378, 1369–1374
  9. Giannone, Domenico, Lucrezia Reichlin, and David Small. "Nowcasting: The real-time informational content of macroeconomic data." Journal of Monetary Economics 55, no. 4, (2008), p 665-676.
  10. Eraker, Bjørn, Ching Wai Chiu, Andrew T. Foerster, Tae Bong Kim, and Hernán D. Seoane. "Bayesian mixed frequency VARs." Journal of Financial Econometrics 13, no. 3, (2014), p 698-721.
  11. Foroni, Claudia, Pierre Guérin, and Massimiliano Marcellino. "Using low frequency information for predicting high frequency variables." International Journal of Forecasting 34, no. 4, (2018), p 774-787.
  12. Reinsel, Gregory C. Elements of multivariate time series analysis. Springer Science & Business Media, 2003.
  13. Ahmed, Mosabber Uddin, and Danilo P. Mandic. "Multivariate multiscale entropy: A tool for complexity analysis of multichannel data." Physical Review 84, no. 6, (2011), p 061918.
  14. He, Hong, and Yonghong Tan. "Unsupervised Classification of Multivariate Time Series Using VPCA and Fuzzy Clustering With Spatial Weighted Matrix Distance." IEEE transactions on cybernetics, (2018).
  15. Meier, Alexander, Claudia Kirch, and Renate Meyer. "Bayesian nonparametric analysis of multivariate time series: A matrix Gamma Process approach." Journal of Multivariate Analysis 175, (2020), p 104560.
  16. Niu, Tong, Jianzhou Wang, Haiyan Lu, Wendong Yang, and Pei Du. "Developing a Deep Learning Framework with Two-Stage Feature Selection for Multivariate Financial Time Series Forecasting." Expert Systems with Applications, (2020), p 113237.
  17. Cui, Zhicheng, Wenlin Chen, and Yixin Chen. "Multi-scale convolutional neural networks for time series classification." arXiv, (2016).
  18. مجتبی بهمنی، آرش جمشید نژاد، محمد صالح انصاری لاری. «بررسی عوامل مؤثر بر مصرف انرژی بخش خانگی استان‌های کشور» فصل‌نامه مطالعات اقتصاد انرژی، سال دهم شماره 42، پاییز 1393.
  19. عباسعلی ابونوری، هادی پرهیزی گشتی، تیمور محمدی. «تجزیه و تحلیل و بررسی عوامل مؤثر بر تقاضای گاز خانگی و تجاری در استان گیلان» فصلنامه علوم اقتصادی سال دوم شماره 5، زمستان 1387.
  20. Timmer, Reed P., and Peter J. Lamb. "Relations between temperature and residential natural gas consumption in the Central and Eastern United States." Journal of applied meteorology and climatology 46, no. 11, (2007), p 1993-2013.
  21. Franco, Alessandro. "Natural gas consumption and correlation with the uses of thermal energy: Analysis of the Italian case." Journal of Natural Gas Science and Engineering 31, (2016), p 703-714.
  22. Liu, Lon-Mu, and Maw-Wen Lin. "Forecasting residential consumption of natural gas using monthly and quarterly time series." International Journal of Forecasting 7, no. 1, (1991), p 3-16.
  23. صادقی، س. ک، موسویان، س.م.، تحلیل آماری و برآورد فاصله ی اطمینان پیش بینی شبکه ی عصبی ARIMA: ترکیبی به منظور مقایسه با مدل خطی (مطالعه ی موردی مصرف ماهانه گاز طبیعی در بخش خانگی ایران، فصلنامه ی تحقیقات مدلسازی اقتصادی، صفحات 106-76، سال 1393.
  24. Asgharpour, H., Behboudi, D., & Ghazvinian, M.H. Structural Failure: Case of Natural Gas Consumption and Economic Growth in Iran. Quarterly Journal of Quantitative Economic 5, (2009), p 105-121, (in Persian).
  25. Lin, W., Chen, B., Luo, S., & Liang, L. Factor analysis of residential energy consumption at the provincial level in China. Sustainability, 6, (2014), p 7710-7724.
  26. Marziali, Andrea, Emanuele Fabbiani, and Giuseppe De Nicolao. "Short-term forecasting of Italian residential gas demand." arXiv, (2019).
  27. Potočnik, Primož, Jurij Šilc, and Gregor Papa. "A comparison of models for forecasting the residential natural gas demand of an urban area." Energy 167, (2019), p 511-522.
  28. Bezdek, James C., Robert Ehrlich, and William Full. "FCM: The fuzzy c-means clustering algorithm." Computers & Geosciences 10, no. 2-3 (1984), p 191-203.
  29. Emmanuel Gbenga Dada1, David Opeoluwa Oyewola, Joseph Hurcha Yakubu and Ayotunde Alaba,”Fadele Predicting Protein Secondary Structure Based On Ensemble Neural Network.’ Journal of Engineering and Technology for Industrial Applications, (2021), p 49-56.
  30. Thaler, Marko, Igor Grabec, and Alojz Poredoš. "Prediction of energy consumption and risk of excess demand in a distribution system." Physica A: Statistical mechanics and its applications 355, no. 1 (2005), p 46-53.
  31. Brabec, Marek, Ondřej Konár, Marek Malý, Emil Pelikán, and Jiří Vondráček. "A statistical model for natural gas standardized load profiles." Journal of the Royal Statistical Society: Series C (Applied Statistics) 58, no. 1 (2009), p 123-139.
Iranian Journal of Gas Engineering
Volume 11, Issue 1 - Serial Number 19
September 2024
Pages 46-70

  • Receive Date 13 April 2024
  • Revise Date 25 May 2024
  • Accept Date 09 June 2024