Forecasting Electricity Demand by Hybrid Machine Learning Model

  • Shu Fan
  • Chengxiong Mao
  • Jiadong Zhang
  • Luonan Chen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


This paper proposes a hybrid machine learning model for electricity demand forecasting, based on Bayesian Clustering by Dynamics (BCD) and Support Vector Machine (SVM). In the proposed model, a BCD classifier is firstly applied to cluster the input data set into several subsets by the dynamics of load series in an unsupervised manner, and then, groups of 24 SVMs for the next day’s electricity demand curve are used to fit the training data of each subset. In the numerical experiment, the proposed model has been trained and tested on the data of the historical load from New York City.


Support Vector Machine Mean Absolute Percentage Error Marginal Likelihood Electricity Demand Load Forecast 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hippert, H.S., Pedreira, C.E., So, R.C.: Neural Networks for Short-Term Load Forecasting: A Review and Evaluation. IEEE Trans. Power Systems 16, 44–55 (2001)CrossRefGoogle Scholar
  2. 2.
    Haida, T., Muto, S.: Regression based peak load forecasting using a transformation technique. IEEE Trans. Power Systems 9, 1788–1794 (1994)CrossRefGoogle Scholar
  3. 3.
    Huang, S.J., Shih, K.R.: Short-term load forecasting via ARMA model identification including nongaussian process considerations. IEEE Trans. Power Systems 18, 673–679 (2003)CrossRefGoogle Scholar
  4. 4.
    Box, G.E.P., Jenkins, G.M.: Time series analysis – forecasting and control. Holden-day, San Francisco (1976)MATHGoogle Scholar
  5. 5.
    Czernichow, T., Piras, A., Imhof, K., Caire, P., Jaccard, Y., Dorizzi, B., Germond, A.: Short term electrical load forecasting with artificial neural networks. Engineering Intelligent Systems 2, 85–99 (1996)Google Scholar
  6. 6.
    Fan, S., Mao, C.X., Chen, L.N.: Peak Load Forecasting Using the Self-organizing Map. In: Wang, J., Liao, X.-F., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3498, pp. 640–647. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Song, K.B., Baek, Y.S., Hong, D.H., Jang, G.: Short-term load forecasting for the holidays using fuzzy linear regression method. IEEE Trans. Power Systems 20, 96–101 (2005)CrossRefGoogle Scholar
  8. 8.
    Fidalgo, J.N., Pecas Lopes, J.A.: Load forecasting performance enhancement when facing anomalous events. IEEE Trans. Power Systems 20, 408–415 (2005)CrossRefGoogle Scholar
  9. 9.
    Chen, B.-J., Chang, M.-W., Lin, C.-J.: Load forecasting using support vector machines: a study on EUNITE competition 2001. IEEE Trans. Power Systems 19, 1821–1830 (2004)CrossRefGoogle Scholar
  10. 10.
    Fan, S., Chen, L.: Short-Term Load Forecasting Based on an Adaptive Hybrid Method. IEEE Trans. Power Systems. 21, 392–401 (2006)CrossRefGoogle Scholar
  11. 11.
    Ramoni, M., Sebastiani, P., Cohen, P.: Bayesian Clustering by Dynamics. Machine Learning 47, 91–121 (2002)MATHCrossRefGoogle Scholar
  12. 12.
    Sebastiani, P., Ramoni, M.: Clustering continuous time series. In: Proc. Eighteenth Int’l Conf. on Machine Learning (ICML-2001), pp. 497–504 (2001)Google Scholar
  13. 13.
  14. 14.
    Cortes, C., Vapnik, V.: Support-vector network. Machine Learning 20, 273–297 (1995)MATHGoogle Scholar
  15. 15.
    Cristianini, N., Shawe-Tylor, J.: An introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press, Cambridge (2000)Google Scholar
  16. 16.
    Chang, C.-C., Lin, C.-J.: LIBSVM: A library for Support Vector Machines (2001), online available:

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Shu Fan
    • 1
  • Chengxiong Mao
    • 2
  • Jiadong Zhang
    • 1
  • Luonan Chen
    • 1
  1. 1.Osaka Sangyo UniversityDaito, OsakaJapan
  2. 2.Huazhong University of Science and TechnologyWuhanChina

Personalised recommendations