Combining STRIPAT model and gated recurrent unit for forecasting nature gas consumption of China

Abstract

With the orderly advancement of China Energy Development Strategic Action Plan, clean energy has become a major trend in the energy market. As a major industry of clean energy, natural gas industry plans to consume at least 10% of the total primary energy by 2020. The energy structure will be improved in an orderly manner to achieve the goal of energy conservation, consumption reduction, and emission reduction. To achieve energy saving and emission reduction, and using clean energy effectively, accurate prediction of natural gas consumption is of great importance. Because of the many influencing factors affecting natural gas demand, this paper first utilizes STRIPAT to analyze the factors affecting natural gas consumption and then uses a deep learning ensemble approach to analyze and predict China’s natural gas consumption. One is an advanced deep neural network model named gated recurrent unit model which is used to model the nonlinear and complex relationships of natural gas consumption with its factors. The other is a powerful ensemble method named bootstrap aggregation which generates multiple data sets for training a set of base models. Our approach combines the advantages of these two technologies to forecast the demand for China’s natural gas market. In empirical research, our method has been tested by some competitive methods and has shown superiority.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

References

  1. Aguilera RF (2014) The role of natural gas in a low carbon Asia Pacific. Appl Energy 113:1795–1800. https://doi.org/10.1016/j.apenergy.2013.07.048

    Article  Google Scholar 

  2. Bengio Y (2013) Deep learning of representations: looking forward// statistical language and speech processing. Springer, Berlin Heidelberg

    Google Scholar 

  3. Bierbaum R, Smith JB, Lee A, Blair M, Carter L, Chapin FS III, Fleming P, Ruffo S, Stults M, McNeeley S, Wasley E, Verduzco L (2013) A comprehensive review of climate adaptation in the United States: more than before, but less than needed. Mitig Adapt Strateg Glob Chang 18(3):361–406

    Article  Google Scholar 

  4. Bingchun L, Chuanchuan F, Arlene B et al (2017) Forecasting of Chinese primary energy consumption in 2021 with GRU artificial neural network. Energies 10(10):1453

    Article  Google Scholar 

  5. Box GEP, Jenkins GM (1971) Time series analysis, forecasting and control. J Am Stat Assoc 134(3)

  6. Breiman L (1996a) Heuristics of instability and stabilization in model selection. Ann Stat 24(6):2350–2383

    Article  Google Scholar 

  7. Breiman L (1996b) Bagging predictors. Mach Learn 24(2):123–140

    Google Scholar 

  8. Charkovska N, Halushchak M, Bun R, Nahorski Z, Oda T, Jonas M, Topylko P (2019) A high-definition spatially explicit modelling approach for national greenhouse gas emissions from industrial processes: reducing the errors and uncertainties in global emission modelling. Mitig Adapt Strateg Glob Chang 24:907–939

    Article  Google Scholar 

  9. Chung J, Hong Y (2007) Model-free evaluation of directional predictability in foreign exchange markets. J Appl Econ 22(5):855–889. https://doi.org/10.1002/jae.965

    Article  Google Scholar 

  10. Claiborne R (1972) The closing circle: nature, man and technology. Hosp Pract 7(2):159–167

    Article  Google Scholar 

  11. Deyun W, Yanling L, Zeng W et al (2018) Scenario analysis of natural gas consumption in China based on wavelet neural network optimized by particle swarm optimization algorithm. Energies 11(4):825. https://doi.org/10.3390/en11040825

    Article  Google Scholar 

  12. Dietz T, Rosa EA (1994) Rethinking the environmental impacts of population, affluence and technology. Hum Ecol Rev 1:277–300

    Google Scholar 

  13. Dietz T, Rosa EA (1997) Effects of population and affluence on CO2 emissions. Proceedings of National Academy of Science, 94, 175–179

  14. Duan H, Zhang G, Wang S, Fan Y (2019a) Integrated benefit-cost analysis of China’s optimal adaptation and targeted mitigation. Ecol Econ 160:76–86

    Article  Google Scholar 

  15. Duan H, Zhang G, Wang S, Fan Y (2019b) Robust climate change research: a review on multi-model analysis. Environ Res Lett 14

  16. Ehrhardt-Martinez K (1998) Social determinants of deforestation in developing countries: a cross-national study. Soc Forces 77(2):567–586

    Article  Google Scholar 

  17. Gers FA, Schmidhuber J, Cummins F (2000) Learning to forget: continual prediction with LSTM. Neural Comput 12(10):2451–2471. https://doi.org/10.1162/089976600300015015

    Article  Google Scholar 

  18. Grushka-Cockayne Y, Jose V R, Lichtendahl K C (2016) Ensembles of overfit and overconfident forecasts. Social Science Electronic Publishing https://doi.org/10.1287/mnsc.2015.2389

  19. Guo-Feng F, An W, Wei-Chiang H (2018) Combining grey model and self-adapting intelligent grey model with genetic algorithm and annual share changes in natural gas demand forecasting. Energies 11(7):1625. https://doi.org/10.3390/en11071625

    Article  Google Scholar 

  20. Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554. https://doi.org/10.1162/neco.2006.18.7.1527

    Article  Google Scholar 

  21. Jarnicka J, Żebrowski P (2019) Learning in greenhouse gas emission inventories in terms of uncertainty improvement over time. Mitig Adapt Strateg Glob Chang 24:1143–1168

    Article  Google Scholar 

  22. Kaytez F, Taplamacioglu MC, Cam E, Hardalac F (2015) Forecasting electricity consumption: a comparison of regression analysis, neural networks and least squares support vector machines. Int J Electr Power Energy Syst 67(67):431–438. https://doi.org/10.1016/j.ijepes.2014.12.036

    Article  Google Scholar 

  23. Khotanzad A, Elragal H, Lu TL (2000) Combination of artificial neural-network forecasters for prediction of natural gas consumption. IEEE Trans Neural Netw 11(2):464–473 https://ieeexplore.ieee.org/document/839015/

    Article  Google Scholar 

  24. Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks//NIPS. Curran Associates Inc., New York

    Google Scholar 

  25. Li J, Dong X, Shangguan J, et al. (2011) Forecasting the growth of Chinese natural gas consumption. Fuel & Energy Abstracts

  26. Lifeng W, Sifeng L, Haijun C, et al. (2015) Using a novel grey system model to forecast natural gas consumption in China. Math Probl Eng

  27. Suykens JAK, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300. https://doi.org/10.1002/(SICI)1097-007X(199911/12)27:6<605::AID-CTA86>3.0.CO;2-Z

    Article  Google Scholar 

  28. Szegedy C, Liu W, Jia Y, et al. (2014) Going deeper with convolutions

  29. Wang T, Lin B (2014) China’s natural gas consumption and subsidies—from a sector perspective. Energy Policy 65:541–551. https://doi.org/10.1016/j.enpol.2013.10.065

    Article  Google Scholar 

  30. York R, Rosa EA, Dietz T (2002) Bridging environmental science with environmental policy: plasticity of population, affluence, and technology. Soc Sci Q 83(1):18–34. https://doi.org/10.1111/1540-6237.00068

    Article  Google Scholar 

  31. Zeng YR, Zeng Y, Choi B, Wang L (2017) Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network. Energy 127:381–396. https://doi.org/10.1016/j.energy.2017.03.094

    Article  Google Scholar 

  32. Zhang W, Yang J (2015) Forecasting natural gas consumption in China by Bayesian model averaging. Energy Rep 1:216–220. https://doi.org/10.1016/j.egyr.2015.11.001

    Article  Google Scholar 

Download references

Funding

This research is supported by self-determined Research Funds of CCNU from the Colleges’ Basic Research and Operation of MOE under Grant No. CCNU19ZN024.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yi Xiao.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Xiao, Y., Li, K., Hu, Y. et al. Combining STRIPAT model and gated recurrent unit for forecasting nature gas consumption of China. Mitig Adapt Strateg Glob Change (2020). https://doi.org/10.1007/s11027-020-09918-1

Download citation

Keywords

  • Natural gas consumption forecasting
  • Emission reduction
  • Deep learning
  • STRIPAT model
  • Gated recurrent unit model
  • Bagging