Methods of Integration of Ensemble of Neural Predictors of Time Series - Comparative Analysis

  • Stanislaw Osowski
  • Krzysztof Siwek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6593)


It is well known fact that organizing different predictors in an ensemble increases the accuracy of prediction of the time series. This paper discusses different methods of integration of predictors cooperating in an ensemble. The considered methods include the ordinary averaging, weighted averaging, application of principal component analysis to the data, blind source separation as well as application of additional neural predictor as an integrator. The proposed methods will be verified on the example of prediction of 24-hour ahead load pattern in the power system, as well as prediction of the environmental pollution for the next day.


time series prediction ensemble of predictors neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chen, B.J., Chang, M.W., Lin, C.J.: Load forecasting using support vector machines: a study on EUNITE competition. IEEE Trans. Power Systems 19, 1245–1248 (2004)Google Scholar
  2. 2.
    Cichocki, A., Amari, S.I.: Adaptive blind signal and image processing. Wiley, N.Y (2003)Google Scholar
  3. 3.
    Haykin, S.: Neural networks, a comprehensive foundation. Macmillan, N.Y (2002)zbMATHGoogle Scholar
  4. 4.
    Hong, W.C.: Hybrid evolutionary algorithms in a SVR-based electric load forecasting model. Intern. Journal of Electrical Power & Energy Systems 31, 409–417 (2009)CrossRefGoogle Scholar
  5. 5.
    Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., Brasseur, O.: A neural network forecast for daily average PM10 concentrations in Belgium. Atmospheric Environ. 39(18), 3279–3289 (2005)CrossRefGoogle Scholar
  6. 6.
    Kandil, N., Wamkeue, R., Saad, M., Georges, S.: An efficient approach for short term load forecasting using ANN. Electr. Power & Energy Systems 28, 525–530 (2006)CrossRefGoogle Scholar
  7. 7.
    Kukkonen, T., et al.: Extensive evaluation of neural networks models for the prediction of NO2 and PM10 concentrations, in central Helsinki. Atmospheric Environment 37, 4539–4550 (2003)CrossRefGoogle Scholar
  8. 8.
    Kuntcheva, L.: Combining pattern classifiers - methods and algorithms. Wiley, N.J (2004)CrossRefGoogle Scholar
  9. 9.
    Mandal, P., Senjyu, T., Urasaki, N., Funabashi, T.: A neural network based several hours ahead electric load forecasting using similar days approach. Electrical Power and Energy Systems 28, 367–373 (2006)CrossRefGoogle Scholar
  10. 10.
    Matlab user manual, user’s guide, MathWorks, Natick (2009)Google Scholar
  11. 11.
    Osowski, S., Siwek, K., Szupiluk, R.: Ensemble neural network approach for accurate load forecasting in the power system. Applied Math. & Computer Sci. 19, 303–315 (2009)zbMATHGoogle Scholar
  12. 12.
    Schölkopf, B., Smola, A.: Learning with kernels. MIT Press, Cambridge (2002)zbMATHGoogle Scholar
  13. 13.
    Siwek, K., Osowski, S.: Two-stage neural network approach to precise 24-hour load pattern prediction. In: Corchado, E., Wu, X., Oja, E., Herrero, Á., Baruque, B. (eds.) HAIS 2009. LNCS (LNAI), vol. 5572, pp. 327–335. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  14. 14.
    Siwek, K., Osowski, S., Sowiński, M.: Neural predictor ensemble for accurate forecasting of PM10 pollution. In: IJCNN, Barcelona, pp. 1–7 (2010)Google Scholar
  15. 15.
    Voukantsis, D., Niska, H., Karatzas, K., Riga, M., Damialis, A., Vokou, D.: Forecasting daily pollen concentrations using data-driven modeling methods. Atmospheric Environmen. 44(39), 5101–5111 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Stanislaw Osowski
    • 1
    • 2
  • Krzysztof Siwek
    • 1
  1. 1.Warsaw University of TechnologyPoland
  2. 2.Military University of TechnologyWarsawPoland

Personalised recommendations