, En définitive, avec deux ans d'apprentissage, les erreurs de prévision restent relativement stables dans le temps

, 1 -Erreur de prévision dans le temps et en fonction de la période d'apprentissage Période d'apprentissage Période test NMAE, TABLE 5, 2015.

, La valeur ajoutée est la contribution au projet DARWIN avec la prévision de la production pour tous les actifs éoliens de la flotte d'ENGIE connectée à DARWIN. Il s'agit d'une innovation tant au niveau du produit lui-même que des moyens utilisés pour le mettre en oeuvre. Tout d'abord, nous industrialisons un modèle de prévision de la production éolienne à la pointe de la technologie qui produit des résultats fiables et robustes. Il a été mis en place dans le cadre de cette thèse et validé dans un "datascience challenge

. Bibliographie, Smoothing methods in statistics, Panorama de l'électricité renouvelable en, 1996.

, Panorama de l'électricité renouvelable au 31 mars 2017, 2017.

, LA RÉGLEMENTATION EN FRANCE. France énergie éolienne, 2019.

R. Baïle, Analyse et modélisation multifractales de vitesses devent. application à la prévision de la ressource éolienne, 2010.

[. Bellanger, , 2006.

, L'analyse des corrélations canoniques appliquée à des données environnementales. Revue de statistique appliquée, vol.54, pp.7-40, 2006.

R. Bellman, Dynamic programming, 1957.

L. Breiman, D. Chakraborty, and N. Pal, Selecting useful groups of features in a connectionist framework, IEEE Neural Networks Council, vol.19, pp.381-96, 2001.

V. Cortes, C. Cortes, and V. Vapnik, Support-vector networks, Machine Learning, 1995.

[. Costa, A review on the young history of the wind power short-term prediction, 2008.

M. Dione-;-dione, Prévision de production éolienne par forêts aléatoires, agrégation et alerte de rampes, Proceedings of the 51es "Journées des Statistiques, 2019.

[. Dione, M. Matzner-løber-;-dione, and E. Matzner-løber, Short-term forecast of wind turbine production with machine learning methods : Direct and indirect approach, Theory and Applications of Time Series Analysis, pp.301-315, 2019.

B. Efron-;-efron, Jackknife-after-bootstrap standard errors and influence functions, Journal of the Royal Statistical Society. Series B (Methodological), pp.83-127, 1992.

B. Efron, Estimation and accuracy after model selection, Journal of the Royal Statistical Society, 2013.

Y. Fanglin, Comparison of forecast skills between ncep gfs four cycles and on the value of 06z and 18z cycles, 2015.

. Feng, C. Zhang-;-feng, and J. Zhang, Wind Power and Ramp Forecasting for Grid Integration, pp.299-315, 2018.

[. Ferreira, A survey on wind power ramp forecasting. Argonne National Laboratory, 2010.

. Frías-paredes, Introducing the temporal distortion index to perform a bidimensional analysis of renewable energy forecast, vol.94, pp.180-194, 2016.

. Frías-paredes, Assessing energy forecasting inaccuracy by simultaneously considering temporal and absolute errors, Energy Conversion and Management, vol.142, pp.433-546, 2017.

Y. Freund and R. E. Schapire, Experiments with a new boosting algorithm, Proceedings of the 13th International Conference on Machine Learning, pp.148-156, 1996.

. Fugon, Data mining for wind power forecasting, European Wind Energy Conference & Exhibition EWEC, p.6, 2008.
URL : https://hal.archives-ouvertes.fr/hal-00506101

[. Fujimoto, Alerting to rare large-scale ramp events in wind power generation, IEEE Transactions on Sustainable Energy, vol.10, issue.1, pp.55-65, 2019.

B. Giebel, G. K. Giebel, and R. Brownsword, The state-of-the-art in short-term prediction of wind power-a literature review, 2003.

. Anemos and . Pdf,

. Gallego-castillo, A review on the recent history of wind power ramp forecasting, Renewable and Sustainable Energy Reviews, vol.52, pp.1148-1157, 2015.

[. Garcia, D. Garcia, A. R. , D. Vega, and E. , A statistical wind power forecasting system -a mexican wind-farm case study, European Wind Energy Conference & Exhibition -EWEC Parc Chanot, 2009.

[. Gastón, Assessing energy forecasting inaccuracy by simultaneously considering temporal and absolute errors, AIP Conference Proceedings 1850, pp.433-546, 2017.

[. Gensler, A review of deterministic error scores and normalization techniques for power forecasting algorithms, IEEE Symposium Series on Computational Intelligence (SSCI), pp.1-9, 2016.

R. Genuer-;-genuer, Forêts aléatoires : aspects théoriques, sélection de variables et applications, 2010.

[. Genuer, Variable selection using random forests, Pattern Recognition Letters, vol.31, pp.2225-2236, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00755489

[. Ghaderi, Deep Forecast : Deep Learning-based Spatio-Temporal Forecasting, 2017.

[. Giebel, The state of the art in short-term prediction of wind power a literature overview, 2011.

G. Giebel and G. Kariniotakis, Best practice in short-term forecasting. a users guide, 2009.
URL : https://hal.archives-ouvertes.fr/hal-00525931

T. Göçmen and G. Giebel, Estimation of turbulence intensity using rotor effective wind speed in lillgrund and horns rev-i offshore wind farms, Renewable Energy, vol.99, pp.524-532, 2016.

[. Gregorutti, Correlation and variable importance in random forests, 2014.
URL : https://hal.archives-ouvertes.fr/hal-00879978

[. Gregorutti, Grouped variable importance with random forests and application to multiple functional data analysis, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01084301

[. Gupta, Wind ramp event prediction with parallelized gradient boosted regression trees, 2016.

[. Guyon, , 2002.

, Gene selection for cancer classification using support vector machines. Machine Learning, vol.46, pp.389-422

T. Hasti, T. Hasti, and R. Tibshirani, Generalized additive models prediction, Statistical Science, 1986.

[. He, A spatiotemporal analysis approach for short-term forecast of wind farm generation, IEEE Transactions on power systems, vol.29, issue.4, pp.1611-1622, 2014.

. Yu, Z. He, and W. Yu, Stable feature selection for biomarker discovery, Computational biology and chemistry, vol.34, pp.215-225, 2010.

H. Hotelling, Relations between two sets variables, Biometrika, vol.28, pp.321-377, 1936.

[. Juban, Uncertainty estimation of wind power forecasts : Comparison of probabilistic modelling approaches, European Wind Energy Conference & Exhibition EWEC, 2008.
URL : https://hal.archives-ouvertes.fr/hal-00506297

G. Kariniotakis and G. Giebel, Wind power forecasting-a review of the state of the art, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01544728

C. ;. Kerns, B. W. Kerns, and S. S. Chen, Ecmwf and gfs model forecast verification during dynamo : Multiscale variability in mjo initiation over the equatorial indian ocean, Journal of Geophysical Research, 2013.

L. Kullback, S. Kullback, and R. Leibler, On information and sufficiency, Annals of Mathematical Statistics, vol.22, pp.79-86, 1951.

[. Kumar, Theoretical and applied climatology, 2017.

[. Kusiak, Wind farm power prediction : a data-mining approach, Wind Energy, vol.12, issue.3, pp.275-293, 2008.

F. Lange, M. Lange, and U. Focken, New developments in wind energy forecasting, IEEE Power and Energy Society General Meeting 2008 -Conversion and Delivery of Electrical Energy in the 21st Century, pp.1-8, 2008.

[. Lenzi, Benefits of spatio-temporal modelling for short term wind power forecasting at both individual and aggregated levels, 2017.

[. Lu, B. Hardin-;-lu, and J. Hardin, Constructing prediction intervals for random forests, 2017.

[. Madsen, Standardizing the performance evaluation of shortterm wind power prediction models, Wind Engineering, vol.29, issue.6, pp.475-489, 2005.

N. Meinshausen, Quantile regression forests, Journal of Machine Learning Research, pp.983-999, 2006.

R. Minkah and T. D. Wet, Comparison of confidence interval estimators : An index approach, 2018.

G. Moreau, S. Moreau, and A. Glorieux-freminet, Chifres clés des énergies renouvelables, 2019.

J. Najac, V. Nzobounsana, and S. Gaymard, Les analyses canoniques simple et généralisée linéaires : applications à des données psychosociales, Math. and Sci. hum. / Mathematics and Social Sciences, vol.1, pp.69-101, 2010.

A. Persson, User guide to ecmwf forecast products, 2015.

, Renewables 2017 global status report, p.21, 2017.

L. Sexton, J. Sexton, and P. Laake, Standard errors for bagged and random forest estimators, Computational Statistics and Data Analysis, vol.53, pp.801-811, 2009.

[. Stone, Classification and regression trees, pp.5-32, 1984.

[. Tastu, Spatiotemporal analysis and modeling of shortterm wind power forecast errors, Wind Energy, vol.14, issue.1, pp.43-60, 2011.

[. Taylor, Wind power density forecasting using ensemble predictions and time series models, IEEE Transactions on Energy Conversion, vol.24, pp.775-782, 2009.

R. Tibshirani, Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society, vol.58, pp.267-288, 1996.

[. Wager, Confidence intervals for random forests : The jackknife and the infinitesimal jackknife, Journal of Machine Learning Research, vol.15, pp.1625-1651, 2014.

[. Wang, A review of wind power forecasting models, Energy Procedia, vol.12, pp.770-778, 2011.

[. Wedam, Comparison of model forecast skill of sea level pressure along the east and west coasts of the united states, p.24, 2009.

F. Yang-;-yang, Review of gfs forecast skills in 2014. Environmental Modeling Center National Centers for Environmental Prediction, 2014.

M. Yuan and Y. Lin, Model selection and estimation in regression with grouped variables, Journal of the Royal Statistical Society, vol.68, pp.49-67, 2006.

[. Zhang, Random forest prediction intervals, The American Statistician, vol.0, issue.0, pp.1-15, 2019.

[. Zhang, Variable selection for the multicategory svm via adaptive sup-norm regularization, Electronic Journal of Statistics, vol.2, pp.149-167, 2008.

[. Zhang, A multivariate and multimodal wind distribution model, Renewable Energy, vol.51, pp.436-447, 2013.

[. Zhang, Ramp forecasting performance from improved short-term wind power forecasting over multiple spatial and temporal scales, Energy, vol.122, pp.528-541, 2017.