Forecasting Electricity Consumption by Aggregating Experts; How to Design a Good Set of Experts

  • Pierre GaillardEmail author
  • Yannig Goude
Conference paper
Part of the Lecture Notes in Statistics book series (LNS, volume 217)


Short-term electricity forecasting has been studied for years at EDF and different forecasting models were developed from various fields of statistics or machine learning (functional data analysis, time series, non-parametric regression, boosting, bagging). We are interested in the forecasting of France’s daily electricity load consumption based on these different approaches. We investigate in this empirical study how to use them to improve prediction accuracy. First, we show how combining members of the original set of forecasts can lead to a significant improvement. Second, we explore how to build various and heterogeneous forecasts from these models and analyze how we can aggregate them to get even better predictions.


Generalize Additive Model Time Instance Aggregation Rule Specialized Expert Learning Parameter 
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.



We thank the anonymous reviewers, the editors, and Gilles Stoltz for their valuable comments and feedback.


  1. 1.
    Aiolfi, M., Capistrán, C., & Timmermann, A. (2010). Forecast combinations (Working Papers 2010-04). Banco de México.
  2. 2.
    Antoniadis, A., Brossat, X., Cugliari, J., & Poggi, J. (2012). Prévision d’un processus à valeurs fonctionnelles en présence de non stationnarités. Application à la consommation d’électricité. Journal de la Société Franaise de Statistique, 153(2), 52–78.MathSciNetGoogle Scholar
  3. 3.
    Antoniadis, A., Brossat, X., Cugliari, J., & Poggi, J. (2013). Clustering functional data using wavelets. International Journal of Wavelets, Multiresolution and Information Processing, 11(1), 1–30.MathSciNetCrossRefGoogle Scholar
  4. 4.
    Antoniadis, A., Paparoditis, E., & Sapatinas, T. (2006). A functional wavelet–kernel approach for time series prediction. Journal of the Royal Statistical Society: Series B, 68(5), 837–857.zbMATHMathSciNetCrossRefGoogle Scholar
  5. 5.
    Azoury, K. S., & Warmuth, M. K. (2001). Relative loss bounds for on-line density estimation with the exponential family of distributions. Machine Learning, 43(3), 211–246.zbMATHCrossRefGoogle Scholar
  6. 6.
    Biau, G., & Patra, B. (2011). Sequential quantile prediction of time series. IEEE Transactions on Information Theory, 57(3), 1664–1674.MathSciNetCrossRefGoogle Scholar
  7. 7.
    Breiman, L. (1996). Bagging predictor. Machine Learning, 24(2), 123–140.zbMATHMathSciNetGoogle Scholar
  8. 8.
    Cesa-Bianchi, N., & Lugosi, G. (2003). Potential-based algorithms in on-line prediction and game theory. Machine Learning, 51(3), 239–261.zbMATHCrossRefGoogle Scholar
  9. 9.
    Cesa-Bianchi, N., & Lugosi, G. (2006). Prediction, learning, and games. Cambridge/ New York: Cambridge University Press.zbMATHCrossRefGoogle Scholar
  10. 10.
    Cho, H., Goude, Y., Brossat, X., & Yao, Q. (2013). Modeling and forecasting daily electricity load curves: A hybrid approach. Journal of the American Statistical Association, 108, 7–21.zbMATHMathSciNetCrossRefGoogle Scholar
  11. 11.
    Cho, H., Goude, Y., Brossat, X., & Yao, Q. (2014, to appear). Modeling and forecasting daily electricity load using curve linear regression. In Lecture notes in statistics 217: Modeling and stochastic learning for forecasting in high dimension, 35–52.Google Scholar
  12. 12.
    Clemen, R. T. (1989). Combining forecasts: A review and annotated bibliography. International Journal of Forecasting, 5(4), 559–583.CrossRefGoogle Scholar
  13. 13.
    Devaine, M., Gaillard, P., Goude, Y., & Stoltz, G. (2013). Forecasting electricity consumption by aggregating specialized experts. Machine Learning, 90(2), 231–260.zbMATHMathSciNetCrossRefGoogle Scholar
  14. 14.
    Eban, E., Birnbaum, A., Shalev-Shwartz, S., & Globerson, A. (2012). Learning the experts for online sequence prediction. In Proceedings of ICML, Edinburgh.Google Scholar
  15. 15.
    Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an applicationto boosting. Journal of Computer and System Sciences, 55, 119–139.zbMATHMathSciNetCrossRefGoogle Scholar
  16. 16.
    Gaillard, P., Goude, Y., & Stoltz, G. (2011). A further look at the forecasting of the electricity consumption by aggregation of specialized experts (Technical report).
  17. 17.
    Gaillard, P., Stoltz, G., & van Erven, T. (2014). A second-order bound with excess losses. ArXiv:1402.2044.Google Scholar
  18. 18.
    Herbster, M., & Warmuth, M. K. (1998). Tracking the best expert. Machine Learning, 32(2), 151–178.zbMATHCrossRefGoogle Scholar
  19. 19.
    Hoerl, A., & Kennard, R. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12, 55–67.zbMATHCrossRefGoogle Scholar
  20. 20.
    Littlestone, N., & Warmuth, M. K. (1994). The weighted majority algorithm. Information and Computation, 108(2), 212–261.zbMATHMathSciNetCrossRefGoogle Scholar
  21. 21.
    Mallet, V. (2010). Ensemble forecast of analyses: Coupling data assimilation and sequential aggregation. Journal of Geophysical Research, 115(D24303), 1–10.Google Scholar
  22. 22.
    Mallet, V., Stoltz, G., & Mauricette, B. (2009). Ozone ensemble forecast with machine learning algorithms. Journal of Geophysical Research, 114(D05307), 1–13.Google Scholar
  23. 23.
    Monteleoni, C., Schmidt, G. A., Saroha, S., & Asplund, E. (2011). Tracking climate models. Statistical Analysis and Data Mining, 4(4), 372–392.MathSciNetCrossRefGoogle Scholar
  24. 24.
    Nedellec, R., Cugliari, J., & Goude, Y. (2014). Gefcom2012: Electric load forecasting and backcasting with semi-parametric models. International Journal of Forecasting, 30(2), 375–381.CrossRefGoogle Scholar
  25. 25.
    Pierrot, A., & Goude, Y. (2011). Short-term electricity load forecasting with generalized additive models. In: Proceedings of ISAP power, Hersonisos, Greece (pp. 593–600).Google Scholar
  26. 26.
    Vovk, V. (2001). Competitive on-line statistics. International Statistical Review, 69(2), 213–248.zbMATHCrossRefGoogle Scholar
  27. 27.
    Vovk, V. G. (1990). Aggregating strategies. In Proceedings of the Third Workshop on Computational Learning Theory, Rochester (pp. 371–386).Google Scholar
  28. 28.
    Wood, S. (2006). Generalized additive models: An introduction with R. Boca Raton: Chapman and Hall/CRC.Google Scholar
  29. 29.
    Wood, S., Goude, Y., & Shaw, S. (2015). Generalized additive models for large datasets. Journal of Royal Statistical Society, Series C, 64(1), 139–155.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.EDF R&D, 1 av du Général de GaulleClamartFrance
  2. 2.GREGHEC, CNRSJouy-en-JosasFrance

Personalised recommendations