Journal of Systems Science and Complexity

, Volume 30, Issue 6, pp 1332–1349 | Cite as

China’s energy consumption forecasting by GMDH based auto-regressive model

  • Ling XieEmail author
  • Jin XiaoEmail author
  • Yi Hu
  • Hengjun Zhao
  • Yi Xiao


It is very significant for us to predict future energy consumption accurately. As for China’s energy consumption annual time series, the sample size is relatively small. This paper combines the traditional auto-regressive model with group method of data handling (GMDH) suitable for small sample prediction, and proposes a novel GMDH based auto-regressive (GAR) model. This model can finish the modeling process in self-organized manner, including finding the optimal complexity model, determining the optimal auto-regressive order and estimating model parameters. Further, four different external criteria are proposed and the corresponding four GAR models are constructed. The authors conduct empirical analysis on three energy consumption time series, including the total energy consumption, the total petroleum consumption and the total gas consumption. The results show that AS-GAR model has the best forecasting performance among the four GAR models, and it outperforms ARIMA model, BP neural network model, support vector regression model and GM (1, 1) model. Finally, the authors give the out of sample prediction of China’s energy consumption from 2014 to 2020 by AS-GAR model.


Auto-regressive model energy demand prediction GMDH small sample forecasting 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Zhu Z X, China Statistical Yearbook, China Statistics Press, Beijing, 2013.Google Scholar
  2. [2]
    Catalina T, Iordache V, and Caracaleanu B, Multiple regression model for fast prediction of the heating energy demand, Energy and Buildings, 2013, 57(3): 302–312.CrossRefGoogle Scholar
  3. [3]
    Pao H T, Fu H C, and Tseng C L, Forecasting of CO2 emissions, energy consumption and economic growth in China using an improved grey model, Energy, 2012, 40(1): 400–409.CrossRefGoogle Scholar
  4. [4]
    Ratrout N T, Short-term traffic flow prediction using group method data handling (GMDH)-based abductive networks, Arabian Journal for Science and Engineering, 2014, 39(2): 631–646.CrossRefGoogle Scholar
  5. [5]
    Yu S, Wei Y M, and Wang K, China’s primary energy demands in 2020: Predictions from an MPSOCRBF estimation model, Energy Conversion and Management, 2012, 61: 59–66.CrossRefGoogle Scholar
  6. [6]
    An N, Zhao W, Wang J, et al., Using multi-output feedforward neural network with empirical mode decomposition based signal filtering for electricity demand forecasting, Energy, 2013, 49(1): 279–288.MathSciNetCrossRefGoogle Scholar
  7. [7]
    Bahrami S, Hooshmand R A, and Parastegari M, Short term electric load forecasting by wavelet transform and grey model improved by PSO (particle swarm optimization) algorithm, Energy, 2014, 72(8): 434–442.CrossRefGoogle Scholar
  8. [8]
    Kavousi-Fard A and Kavousi-Fard F, A new hybrid correction method for short-term load forecasting based on ARIMA, SVR and CSA, Journal of Experimental and Theoretical Artificial Intelligence, 2013, 25(4): 559–574.CrossRefGoogle Scholar
  9. [9]
    Wu Z and Xu J, Predicting and optimization of energy consumption using system dynamics-fuzzy multiple objective programming in world heritage areas, Energy, 2013, 49(1): 19–31.CrossRefGoogle Scholar
  10. [10]
    Pindyck R S and Rubinfeld D L, Econometric Models and Economic Forecasts, Irwin/McGraw-Hill, Boston, 1998.Google Scholar
  11. [11]
    Erdogdu E, Electricity demand analysis using cointegration and ARIMA modelling: A case study of Turkey, Energy Policy, 2007, 35(2): 1129–1146.CrossRefGoogle Scholar
  12. [12]
    Deng J, Grey Prediction and Decision, Huazhong University of Science and Technology Press, Wuhan, China, 1986.Google Scholar
  13. [13]
    Akay D and Atak M, Grey prediction with rolling mechanism for electricity demand forecasting of Turkey, Energy, 2007, 32(9): 1670–1675.CrossRefGoogle Scholar
  14. [14]
    Chen C I and Huang S J, The necessary and sufficient condition for GM (1, 1) grey prediction model, Applied Mathematics and Computation, 2013, 219(11): 6152–6162.MathSciNetzbMATHCrossRefGoogle Scholar
  15. [15]
    Nilsson N J, Principles of Artificial Intelligence, Morgan Kaufmann, San Francisco, 2014.zbMATHGoogle Scholar
  16. [16]
    Unler A, Improvement of energy demand forecasts using swarm intelligence: The case of Turkey with projections to 2025, Energy Policy, 2008, 36(6): 1937–1944.CrossRefGoogle Scholar
  17. [17]
    Hu X M and Zhao G, Forecasting model of coal demand based on Matlab BP neural network, Chinese Journal of Management Science, 2008, 10(16): 521–525.Google Scholar
  18. [18]
    Yu S and Zhu K, A hybrid procedure for energy demand forecasting in China, Energy, 2012, 37(1): 396–404.CrossRefGoogle Scholar
  19. [19]
    Xiao J, Xiao Y, Fu J L, et al., A transfer forecasting model for container throughput guided by discrete PSO, Journal of Systems Science and Complexity, 2014, 27(1): 181–192.zbMATHCrossRefGoogle Scholar
  20. [20]
    Xiao Y, Xiao J, Lu F B, et al., Ensemble ANNs-PSO-GA approach for day-ahead stock eexchange prices forecasting, International Journal of Computational Intelligence Systems, 2013, 7(2): 272–290.MathSciNetCrossRefGoogle Scholar
  21. [21]
    Kiran M S, Ozceylan E, Gunduz M, et al., A novel hybrid approach based on particle swarm optimization and ant colony algorithm to forecast energy demand of Turkey, Energy Conversion and Management, 2012, 53(1): 75–83.CrossRefGoogle Scholar
  22. [22]
    Madala H R and Ivakhnenko A G, Inductive Learning Algorithms for Complex Systems Modeling, CRC Press, Boca Raton, 1994.zbMATHGoogle Scholar
  23. [23]
    Ivakhnenko A G, Polynomial theory of complex systems, IEEE Transactions on Systems, Man and Cybernetics, 1971, 1(4): 364–378.CrossRefGoogle Scholar
  24. [24]
    Ivakhnenko A G, The review of problems solvable by algorithms of the group method of data handling (GMDH), Pattern Recognition and Image Analysis, 1995, 5(4): 527–535.Google Scholar
  25. [25]
    He C Z, Self-organizing Data Mining and Economic Forecasting, Science Publish, Beijing, 2005.Google Scholar
  26. [26]
    Kialashaki A and Reisel J R, Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States, Energy, 2014, 76(11): 749–760.CrossRefGoogle Scholar
  27. [27]
    Zhang G P, Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, 2003, 50(1): 159–175.zbMATHCrossRefGoogle Scholar
  28. [28]
    Vapnik V, The Nature of Statistical Learning Theory, Springer, Berlin, 1999.zbMATHGoogle Scholar
  29. [29]
    Kialashaki A and Reisel J R, Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States, Energy, 2014, 76(11): 749–760.CrossRefGoogle Scholar
  30. [30]
    Jain R K, Smith K M, Culligan P J, et al., Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy, Applied Energy, 2014, 123(6): 168–178.CrossRefGoogle Scholar
  31. [31]
    Deng J L, Grey Control System, Printing House of Central China University of Science and Technology, Hubei, 1985.zbMATHGoogle Scholar
  32. [32]
    Liu S F and Forrest J, The role and position of grey system theory in science development, The Journal of Grey System, 1997, 9(4): 351–356.Google Scholar
  33. [33]
    Deng J L, Introduction to grey system theory, The Journal of Grey System, 1989, 1(1): 1–24.MathSciNetzbMATHGoogle Scholar
  34. [34]
    Lai I C, Chang Y, Lee C, et al., Source identification and characterization of atmospheric polycyclic aromatic hydrocarbons along the southwestern coastal area of Taiwan — With a GMDH approach, Journal of Environmental Management, 2013, 115(1): 60–68.CrossRefGoogle Scholar
  35. [35]
    Mrugalski M, An unscented Kalman filter in designing dynamic GMDH neural networks for robust fault detection, International Journal of Applied Mathematics and Computer Science, 2013, 23(1): 157–169.MathSciNetzbMATHCrossRefGoogle Scholar
  36. [36]
    Xiao J, He C Z, Jiang X, et al., A dynamic classifier ensemble selection approach for noise data, Information Sciences, 2010, 180(18): 3402–3421.CrossRefGoogle Scholar
  37. [37]
    Teng G E, He C Z, Xiao J, et al., Customer credit scoring based on HMM/GMDH hybrid model, Knowledge and Information Systems, 2013, 36(3): 731–747.CrossRefGoogle Scholar
  38. [38]
    Xiao J, He C Z, and Jiang X Y, Structure identification of Bayesian classifiers based on GMDH, Knowledge-Based Systems, 2009, 22(6): 461–470.CrossRefGoogle Scholar

Copyright information

© Institute of Systems Science, Academy of Mathematics and Systems Science, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Business SchoolSichuan UniversityChengduChina
  2. 2.School of Economics and ManagementUniversity of Chinese Academy of SciencesBeijingChina
  3. 3.School of Economics and ManagementSichuan Radio and TV UniversityChengduChina
  4. 4.School of Information ManagementCentral China Normal UniversityWuhanChina

Personalised recommendations