Abstract
In this paper we provide a prediction method, the prediction box, based on a sparse learning process elaborated on very high dimensional information, which will be able to include new – potentially high dimensional – influential variables and adapt to different contexts of prediction. We elaborate and test this method in the setting of predicting the national French intra day load curve, over a period of time of 7 years on a large data basis including daily French electrical consumptions as well as many meteorological inputs, calendar statements and functional dictionaries. The prediction box incorporates a huge contextual information coming from the past, organizes it in a manageable way through the construction of a smart encyclopedia of scenarios, provides experts elaborating strategies of prediction by comparing the day at hand to referring scenarios extracted from the encyclopedia, and then harmonizes the different experts. More precisely, the prediction box is built using successive learning procedures: elaboration of a data base of historical scenarios organized on a high dimensional and functional learning of the intra day load curves, construction of expert forecasters using a retrieval information task among the scenarios, final aggregation of the experts. The results on the national French intra day load curves strongly show the benefits of using a sparse functional model to forecast the electricity consumption. They also appear to meet quite well with the business knowledge of consumption forecasters and even shed new lights on the domain.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Antoniadis, A., Brossat, X., Cugliari, J., & Poggi, J. M. (2010). Clustering functional data using wavelets. In Proceedings of the 19th international conference on computational statistics, COMPSTAT, Paris, 697–704.
Antoniadis, A., Brossat, X., Cugliari, J., & Poggi, J. M. (2012). Prévision d’un processus à valeurs fonctionnelles en présence de non stationnarités. Application à la consommation d’électricité. Journal de la Société; Française de Statistique, 153(2), 52–78.
Antoniadis, A., Paparoditis, E., & Sapatinas, T. (2006). A functional wavelet–kernel approach for time series prediction. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 68(5), 837–857.
Catoni, O. (2004). Statistical learning theory and stochastic optimization, volume 1851 of Lecture notes in mathematics. Berlin: Springer.
Chakhchoukh, Y., Panciatici, P., & Bondon, P. (2009). Robust estimation of SARIMA models: Application to short-term load forecasting. In IEEE workshop on statistical signal processing, Cardiff
Cho, H., Goude, Y., Brossat, X., & Yao, Q. (2013). Modelling and forecasting daily electricity load curves: A hybrid approach. Journal of the American Statistical Association, 108(501), 7–21.
Dalalyan, A. S., & Tsybakov, A. B. (2008). Aggregation by exponentiel weighting, sharp oracle inequalities and sparsity. In COLT, Helsinki (pp. 97–111).
Devaine, M., Gaillard, P., Goude, Y., & Stoltz, G. (2012). Forecasting electricity consumption by aggregating specialized experts. Machine Learning, 90, 1–30.
Fan, S., & Hyndman, R. J. (2010). Density forecasting for long-term peak electricity demand. IEEE Transactions on Power Systems, 25(2), 1142–1152.
Fan, S., & Hyndman, R. J. (2012). Short-term load forecasting based on a semi-parametric additive approach. IEEE Transactions on Power Systems, 27(1), 134–140.
Juditsky, A. B., & Nemirovski, A. S. (2000). Functional aggregation for nonparametric regression. The Annals of Statistics, 28(3), 681–712.
Kerkyacharian, G., Mougeot, M., Picard, D., & Tribouley, K. (2009). Learning out of leaders. In Multiscale, nonlinear and adaptive approximation (Lecture notes in computer science). Berlin: Springer.
Lefieux, V. (2007). Modèles semi-paramétriques appliqués à la prévision des séries temporelles: cas de la consommation d’ électricité.
Marin, F. J., Garcia-Lagos, F., & Sandoval, F. (2002). Global model for short term load forecasting using artificial neural networks. IEE Proceedings – Generation, Transmission, and Distribution, 149, 121–125.
Mougeot, M., Picard, D., & Tribouley, K. (2012). Learning out of leaders: Regression for high dimension. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 74, 475–513.
Mougeot, M., Picard, D., & Tribouley, K. (2014). LOL selection in high dimension. Computational Statistics and Data Analysis, 71, 743–757.
Mougeot, M., Picard, D., Tribouley, K., Lefieux, V., & Maillard-Teyssier, L. (2013). Sparse approximation and fit of intraday load curves in a high dimentional framework. Advanced in Adaptive Data Analysis, 5. http://www.worldscientific.com/doi/pdf/10.1142/S1793536913500167.
Muñoz, A., Sánchez-Úbeda, E. F., Cruz, A., & Marin, J. (2010). Short-term forecasting in power systems: A guided tour. In Handbook of power systems II (pp. 129–160). Berlin/Heidelberg: Springer.
Poggi, J. M. (1994). Prévision non paramétrique de la consommation d’électricité. Revue de Statistique Appliquée, 42, 83–98.
Ramsay, J. O., & Silverman B. W. (2005). Functional data analysis. New York: Springer.
Taylor, J. W. (2010). Triple seasonal methods for short-term electricity demand forecasting. European Journal of Operational Research, 204(1), 139–152.
Taylor, J. W. (2012). Short-term load forecasting with exponentially weighted methods. IEEE Transactions on Power Systems, 27, 458–464.
Tsybakov, A. B. (2003). Optimal rates of aggregation. In COLT, Washington, DC (pp. 303–313).
Acknowledgements
The authors thank RTE for the financial support through two industrial contracts, LPMA for hosting our researches, and Karine Tribouley for taking part of an earlier elaboration of this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Mougeot, M., Picard, D., Lefieux, V., Maillard-Teyssier, L. (2015). Forecasting Intra Day Load Curves Using Sparse Functional Regression. In: Antoniadis, A., Poggi, JM., Brossat, X. (eds) Modeling and Stochastic Learning for Forecasting in High Dimensions. Lecture Notes in Statistics(), vol 217. Springer, Cham. https://doi.org/10.1007/978-3-319-18732-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-18732-7_9
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-18731-0
Online ISBN: 978-3-319-18732-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)