Développement de méthodes pour la prédiction de la production éolienne régionale.

Accueil || Parcours || Recherche || S'enregistrer || Mon Compte || Contacts || Aide || Langues

Siebert, Nils (2008) Développement de méthodes pour la prédiction de la production éolienne régionale. Doctorat Energétique, CEP - Centre Energétique et Procédés, ENSMP p.265.

Plein texte disponible en tant que : - PhD_Siebert.pdf ( 3821 Kb )

Licence: Copyright

Autres Localisations: http://tel.archives-ouvertes.fr/tel-00287551/fr/

Résumé

L'intégration à grande échelle de l'énergie éolienne dans les réseaux électriques peut poser des problèmes aux opérateurs de ces réseaux car, contrairement aux moyens de production conventionnels, la production éolienne est variable et non contrôlable. Pour réduire l’impact de certains de ces problèmes, les gestionnaires de réseaux expriment le besoin de prévisions à court terme (de 48 à 120 heures) de la production agrégée des parcs éoliens situés dans une région définie.

Le but de la thèse est de développer un cadre d’analyse et des outils permettant de faciliter la mise en place de modèles de prévision de la production éolienne régionale.

La thèse présente tout d’abord un cadre d’analyse permettant de caractériser la production éolienne régionale. Par ce biais, les propriétés saillantes de la production régionale, qui doivent être prises en compte lors de la conception d’un modèle de prévision régionale, sont identifiées.

Le problème de la prévision régionale est ensuite abordé comme un problème d’apprentissage statistique. Nous définissons trois approches de modélisation générique permettant la combinaison de sous-modèles. L’influence de ces approches sur la précision des prévisions est étudiée ainsi que celle du choix des sous-modèles. Pour permettre la comparaison de sous-modèles, nous introduisons un modèle de prévision éolienne dont la performance est comparable aux modèles de l’état de l’art.

Finalement, nous examinons l’impact sur la précision de prévision qu’a le choix des variables explicatives et nous proposons des règles générales de sélection dans le cadre de la prévision éolienne régionale. Pour faciliter le processus de modélisation, des méthodes de sélection automatique sont étudiées. Deux méthodes (une méthode filtre et une méthode wrapper) qui exploitent les caractéristiques propres au problème sont proposées. Nous montrons que ces méthodes sont plus performantes qu’une méthode générique de l’état de l’art.

Références Bibliographiques

[1] International Panel on Climate Change, Climate Change 2001: The Scientific Basis. Contribution of Working Group I to the Third Assessment Report of the Intergovernmental Panel on Climate Change, J. Houghton, Y. Ding, D. Griggs, M. Noguer, P. van der Linden, X. Dai, K. Maskell, and C. Johnson, Eds. Cambridge, United Kingdom and New York, NY, USA,: Cambridge University Press, 2001. [Online]. Available: http://www.grida.no/climate/ipcc_tar/wg1/index.htm

[2] International Energy Agency, World Energy Outlook 2004. IEA PUBLICATIONS, 2004. [Online]. Available: http://www.iea.org/textbase/nppdf/free/2004/weo2004.pdf

[3] ——, “The global renewable energy policies and measures database,” Website, June 2006. [Online]. Available: http://renewables.iea.org

[4] “Directive 2001/77/ec of the european parliament and of the council of 27 september 2001 on the promotion of electricity produced from renewable energy sources in the internal electricity market,” Official Journal of the European Commission, vol. L 283, pp. 33–40, 2001. [Online]. Available: http://europa.eu.int/eur-lex/pri/en/oj/dat/2001/l_283/l_28320011027en00330040.pdf

[5] L. Bird, M. Bolinger, T. Gagliano, R. Wiser, M. Brown, and B. Parsons, “Policies and market factors driving wind power development in the united states,” Energy Policy, vol. 33, no. 11, pp. 1397–1407, July 2005. [Online]. Available: http://www.sciencedirect.com/science/article/B6V2W-4BRSFC9-1/2/d7c7da67036a7bc64f146248116d34f4

[6] Ministry of Non-Conventional Energy Sources Government of India, Annual Report 2005-2006, 2006. [Online]. Available: http://mnes.nic.in/frame.htm?majorprog.htm

[7] Global Wind Energy Council, “Global wind 2006 report,” Global Wind Energy Council, Brussels, Belgium, Tech. Rep., 2006. [Online]. Available: http://www.gwec.net/fileadmin/documents/Publications/gwec-2006_final_01.pdf

[8] M. Hoogwijk, B. de Vries, and W. Turkenburg, “Assessment of the global and regional geographical, technical and economic potential of onshore wind energy,” Energy Economics, vol. 26, no. 5, pp. 889–919, Sept. 2004. [Online]. Available: http://www.sciencedirect.com/science/article/B6V7G-4CX6XY1-1/2/4233dcd7ca19dd51b566a0438aabc1d4255

[9] Global Wind Energy Council, “Global wind 2005 report,” Global Wind Energy Council, Brussels, Belgium, Tech. Rep., 2005. [Online]. Available: http://www.gwec.net/fileadmin/documents/Publications/Global_WindPower_05_Report.pdf

[10] P. A. Østergaard, “Ancillary services and the integration of substantial quantities of wind power,” Applied Energy, vol. 83, no. 5, pp. 451–463, May 2006. [Online]. Available: http://www.sciencedirect.com/science/article/B6V1T-4GKWJ77-2/2/e30278d384303f8de323e06d2fe2027b

[11] D. Anderson and M. Leach, “Harvesting and redistributing renewable energy: on the role of gas and electricity grids to overcome intermittency through the generation and storage of hydrogen,” Energy Policy, vol. 32, no. 14, pp. 1603–1614, Sept. 2004. [Online]. Available: http://www.sciencedirect.com/science/article/B6V2W-49CN3VC-1/2/9eb357d90ddba2736e32bd4f664b864d

[12] F. Graves, T. Jenkin, and D. Murphy, “Opportunities for electricity storage in deregulating markets,” The Electricity Journal, vol. 12, no. 8, pp. 46–56, Oct. 1999. [Online]. Available: http://www.sciencedirect.com/science/article/B6VSS-3XV2K6H-6/2/9600585ac5037a6bf7d974010576e1dd

[13] P. Denholm, “Improving the technical, environmental and social performance of wind energy systems using biomass-based energy storage,” Renewable Energy, vol. 31, no. 9, pp. 1355–1370, July 2006. [Online]. Available: http://www.sciencedirect.com/science/article/B6V4S-4GY870M-1/2/c32ddbf68374596fa6817f4986c7056d

[14] E. Castronuovo and J. Lopes, “On the optimization of the daily operation of a wind-hydro power plant,” Power Systems, IEEE Transactions on, vol. 19, no. 3, pp. 1599–1606, 2004.

[15] R. Castro and L. Ferreira, “A comparison between chronological and probabilistic methods to estimate wind power capacity credit,” Power Systems, IEEE Transactions on, vol. 16, no. 4, pp. 904–909, 2001.

[16] M. Grubb, “Value of variable sources on power systems,” Generation, Transmission and Distribution [see also IEE Proceedings-Generation, Transmission and Distribution], IEE Proceedings C, vol. 138, no. 2, pp. 149–165, 1991.

[17] P. Eriksen, T. Ackermann, H. Abildgaard, P. Smith,W.Winter, and J. Rodriguez Garcia, “System operation with high wind penetration,” Power and Energy Magazine, IEEE, vol. 3, no. 6, pp. 65–74, 2005.

[18] E. DeMeo, W. Grant, M. Milligan, and M. Schuerger, “Wind plant integration [wind power plants],” Power and EnergyMagazine, IEEE, vol. 3, no. 6, pp. 38–46, 2005.

[19] E. Fagan, S. Grimes, J. McArdle, P. Smith, and M. Stronge, “Grid code provisions for wind generators in ireland,” in Power Engineering Society General Meeting, 2005. IEEE, 2005, pp. 1241–1247 Vol. 2.

[20] RTE, “Bilan prévisionel de l’équilibre offre demande d’électricité en France,” Gestionnaire du Réseau de Transport d’Electricité, Tech. Rep., 2005.

[21] S.-V. Thor and P. Weis-Taylor, “Long-term research and development needs for wind energy for the time frame 2000-2020,” Wind Energy, vol. 5, no. 1, pp. 73–75, 2002. [Online]. Available: http://dx.doi.org/10.1002/we.65

[22] R. Kimura, “Numerical weather prediction,” Journal of Wind Engineering and Industrial Aerodynamics, vol. 90, no. 12-15, pp. 1403–1414, Dec. 2002. [Online]. Available: http://www.sciencedirect.com/science/article/B6V3M-476JXKB-6/2/a1fa97cbfb73070a1494354df93328fa256

[23] B. F. Hobbs, M. H. Rothkopf, R. P. O’Neil, and H.-p. Chao, Eds., The Next Generation of Electric Power Unit Commitment Models, ser. International Series in Operations Research & Management Science. Dordrecht: Kluwer Academic Publishers, 2001.

[24] U. Focken, M. Lange, K. Mönnich, H. G. Waldl, H.-P.andBeyer, and A. Luig, “Shortterm prediction of the aggregated power output of wind farms - a statistical analysis of the reduction of the prediction error by spatial smoothing effects,” Journal of Wind Engineering and Industrial Aerodynamics, vol. 90, no. 3, pp. 231–246, Mar. 2002. [Online]. Available: http://www.sciencedirect.com/science/article/B6V3M-44Y0X3R-1/2/e22ae2cbfc04e5d029065a3ad14b20fe

[25] G. Kariniotakis, G. S. Stavrakakis, and E. Nogaret, “Wind power forecasting using advanced neural networks models,” IEEE Transactions on Energy Conversion, vol. 11, no. 4, pp. 762–767, Dec. 1996.

[26] H.Madsen, P. Pinson, G. Kariniotakis, H. A. Nielsen, and T. S. Nielsen, “Standardizing the performance evaluation of shorttermwind power prediction models,”Wind Engineering, vol. 29, no. 6, pp. 475–485, Dec. 2005.

[27] G. Kariniotakis, P. Pinson, N. Siebert, G. Giebel, and R. Barthelmie, “The state of the art in short-term prediction of wind power - from an offshore perspective,” in Proceeding of the 2004 SeaTechWeek, Brest, France, 20-21 October 2004. [Online]. Available: http://anemos.cma.fr/modules.php?name=News&file=article&sid=17

[28] G. Giebel, G. Kariniotakis, and R. Brownsword, “The state-of-the-art in short-term prediction of wind power - from a danish perspective,” in Proceedings of the 4th International Workshop on Large-Scale Integration ofWind Power and TransmissionNetworks for OffshoreWind Farms, Billund, Denmark, 21-23 October 2003.

[29] S. Heier, Grid integration of wind energy conversion systems. Chichester ; New York: Wiley, 1998.

[30] G. E. P. Box and G. M. Jenkins, Time Series Analysis forecasting and control, revised ed., ser. Holden-Day series in Time Series Analysis and Digital Processing, R. Enders, Ed. Oakland, California, USA: Holden-Day, 1976.

[31] M. Milligan, M. N. Schwartz, and Y. Wan, “Statistical wind power forecasting for u.s. wind farms,” National Renewable Energy Laboratory, 1617 Cole Boulevard, Golden, Colorado, Research Report NREL/CP-500-35087, Nov. 2003.

[32] G. Kariniotakis, I. Martí, D. Casas, P. Pinson, T. S. Nielsen, H. Madsen, J. Giebel, G. andUsaola, I. Sanchez, A. M. Palomares, R. Brownsword, J. Tambke, U. Focken, P. Lange, M. andLouka, G. Kallos, C. Lac, G. Sideratos, and G. Descombes, “What performance can be expected by short-term wind power prediction models depending on site characteristics?” in Proceedings of the 2004 European Wind Energy Association Conference EWEC’04, London, UK., Nov. 2004. [Online]. Available: http://www.2004ewec.info/files/23_1400_georgekariniotakis_01.pdf

[33] C. Chatfield, Time-series forecasting. Boca Raton: Chapman & Hall/CRC, 2000.

[34] H.Madsen, G. Kariniotakis, H. A. Nielsen, T. S. Nielsen, and P. Pinson, “A protocol for standardising the performance evaluation of short-term wind power prediction models,” in Proceedings of the GlobalWindPower 2004 Conference, Chicago, Illinois,Mar. 2004.

[35] S. Lang, J. Möhrlen, J. Jørgensen, B. O. Gallachóir, and E. McKeogh, “Application of a multi-scheme ensemble prediction system for wind power forecasting in ireland and comparison with validation results from denmark and germany,” in Proceedings of the 2006 European Wind Energy Conference, EWEC’06, Athens, Greece, 2006. [Online]. Available: http://www.ewec2006proceedings.info/257

[36] P. Pinson, “Estimation of the uncertainty in wind power forecasting,” Ph.D. dissertation, Ecole desMines de Paris, Center for Energy and Processes, Rue Claude Daunesse, Sophia Antipolis, 2006.

[37] T. S. Nielsen, A. Joensen, H. Madsen, L. Landberg, and G. Giebel, “A new reference for wind power forecasting,” Wind Energy, vol. 1, no. 1, pp. 29–34, 1998. [Online]. Available: http://dx.doi.org/10.1002/(SICI)1099-1824(199809)1:1<29::AID-WE10>3.0.CO;2-B

[38] P. Pinson, N. Siebert, and G. Kariniotakis, “Forecasting of regional wind generation by a dynamic fuzzy-neural networks based upscaling approach,” in Proceedings of the 2003 European Wind Energy Association Conference EWEC’03,Madrid, Spain, 16-19 July 2003.

[39] E. Nogaret, G. Stavrakakis, J. Bonin, G. Kariniotakis, B. Papadias, G. Contaxis, M. Papadopoulos, N. Hatziargyriou, S. Papathanassiou, J. Garopoulos, E. Karagounis, J. Halliday, G. Dutton, J. Pedas-Lopes, A. Androutsos, and P. Pligoropoulos, “Development and implementation of an advanced control system for medium size wind-diesel systems.” in Proceedings of the 1994 European Wind Energy Association Conference EWEC’94, Thesaloniki, Greece, Oct. 1994, pp. 599–604.

[40] S. Makridakis, S. C. Wheelwright, and V. E. McGee, Forecasting : methods and applications, 2nd ed. JohnWiley & Sons, 1983.

[41] H. Fukuda, S. Tamaki, M. Nakamura, H. Nagai, F. Shijo, S. Asato, and K. Onaga, “The development of a wind velocity prediction method based on a data mining type auto-regressive model,” in Proceedings of the 2001 European Wind Energy Association Conference EWECŠ01, Copenhagen, Denmark, July 2001, pp. 741–744.

[42] M. J. Durán, D. Cros, and J. Riquelme, “Short-term wind power prediction based on ar models,” in Proceedings of the 9th Spanish-Portuguese Congress on Electrical Engineering, 2005. [Online]. Available: http://www.aedie.org/9CHLIE-paper-send/374DURAN.pdf

[43] A. Dutton, G. Kariniotakis, J. Halliday, and E. Nogaret, “Load and wind power forecasting methods for the optimal management of isolated power systems with high wind penetration,” Wind Engineering, vol. 23, no. 2, pp. 69–87, 1999.

[44] M. C. Alexiadis, P. S. Dokopoulos, and H. S. Sahsamanoglou, “Wind speed and power forecasting based on spatial correlation models,” IEEE Transactions on Energy Conversion, vol. 14, no. 3, pp. 836–842, Sept. 1999.

[45] S. Li, D. C. Wunsch, E. A. OŠHair, and M. G. Giesselmann, “Using neural networks to estimate wind turbine power generation,” IEEE Transactions on Energy Conversion, vol. 16, no. 3, pp. 276–282, Sept. 2001.

[46] G. Kariniotakis, “Contribution au développement d’un système de contrôle avancé pour les systèmes éolien-diesel autonomes,” Ph.D. dissertation, Ecole des Mines de Paris, Center for Energy Studies, Rue Claude Daunesse, Sophia Antipolis, Dec. 1996.

[47] A. Sfetsos, “Time series forecasting of wind speed and solar radiation for renewable energy sources,” Ph.D. dissertation, Imperial College, London, 1999.

[48] ——, “A comparison of various forecasting techniques applied to mean hourly wind speed time series,” Renewable Energy, vol. 21, no. 1, pp. 23–35, Sept. 2000.

[49] S. Enomoto, N. Inomata, T. Yamada, H. Chiba, R. Tanikawa, T. Oota, and H. Fukuda, “Prediction of power output from wind farm using local meteorological analysis,” in Proceedings of the 2001 European Wind Energy Conference, EWEC’01, Copenhagen, Denmark, July 2001, pp. 822–825.

[50] M.Magnusson and L.Wern, “Wind energy predictions using cfd and hirlam forecasts,” in Proceedings of the 2001 EuropeanWind Energy Conference, EWEC’01, Copenhagen,Denmark, July 2001, pp. 861–863.

[51] J.-M. Noël and R. Chevallaz-Perrier, “Wind resource assessment with ariawind in a complex site,” in Proceedings of the 2001 European Wind Energy Conference, EWEC’01, Copenhagen, Denmark, July 2001, pp. 872–874.

[52] I. Troen and E. L. Petersen, EuropeanWind Atlas. Roskilde, Denmark: Risø National Laboratory, 1989.

[53] L. Landberg, “Short-term prediction of local wind conditions,” Journal of Wind Engineering and Industrial Aerodynamics, vol. 89, no. 3-4, pp. 235–245, Mar. 2001. [Online]. Available: http://www.sciencedirect.com/science/article/B6V3M-42DP3K0-3/2/1d5079d0f591faa0b5fe22392089d20b

[54] R. Watson, L. Landberg, R. Costello, D.McCoy, and P. OŠDonnell, “Evaluation of the prediktor wind power forecasting system in ireland,” in Proceedings of the 2001 European Wind Energy Conference, EWEC’01, Copenhagen, Denmark, July 2001, pp. 861–863.

[55] G. Giebel, L. Landberg, T. S. Nielsen, and H. Madsen, “The zephyr-project : The next generation prediction system,” in Proceedings of the 2001 European Wind Energy Conference, EWEC’01, Copenhagen, Denmark, July 2001, pp. 777–780.

[56] H. G. Beyer, D. Heinemann, H.Mellinghoff, K. Mönnich, and H.-P.Waldl, “Forecast of regional wind power output of wind turbines,” in Proceedings of the 1999 European Wind Energy Conference, EWEC’99, Nice, France,Mar. 1999, pp. 1070–1073.

[57] U. Focken, M. Lange, and H.-P. Waldl, “Previento: a wind power prediction system with an innovative upscaling algorithm,” in Proceedings of the 2001 EuropeanWind Energy Association Conference EWEC’01, Copenhagen, Denmark, 2-6 July 2001, pp. 826–829.

[58] I.Martí, D. Cabezón, J. Villanueva, M. J. Sanisidro, Y. Loureiro, E. Cantero, and J. Sanz, “Localpred and Regiopred. Advanced tools for wind energy prediction in complex terrain,” in Proceedings of the EuropeanWind Energy Conference EWEC’03,Madrid, Spain, 16-19 June 2003.

[59] B. Bailey, M. C. Brower, and J. Zack, “Short-term wind forecasting ˝U development and application of a mesoscale model,” in Proceedings of the 1999 European Wind Energy Conference, EWEC’99, Nice, France,Mar. 1999, pp. 1062–1065.

[60] T. S. Nielsen, H.Madsen, and J. Tøfting, “Experiences with statistical methods for wind power prediction,” in Proceedings of the 1999 European Wind Energy Conference, EWEC’99, Nice, France,Mar. 1999, pp. 1066–1069.

[61] T. S.Nielsen and H.Madsen, “Statistical methods for predicting wind power,” in Proceedings of the 1997 EuropeanWind Energy Conference, EWEC’97, Dublin, Ireland, Oct. 1997, pp. 755–758.

[62] L.-X. Wang, Adaptive fuzzy systems and control : design and stability analysis. Englewood Cliffs, N.J.: PTR Prentice Hall, 1994, li-Xin Wang.; Includes bibliographical references (p. 221-227) and index.

[63] G. Kariniotakis, E. Nogaret, A. Dutton, J. Halliday, and A. Androutsos, “Evaluation of advanced wind power and load forecasting methods for the optimal management of isolated power systems,” in Proceedings of the 1999 European Wind Energy Conference, EWEC’99, Nice, France, Mar. 1999, pp. 1082–1085.

[64] G. Kariniotakis and D. Mayer, “An advanced on-line wind resource prediction system for the optimal management of wind parks,” in 3rdMedPower Conference, Athens, Greece, Nov. 2002.

[65] I. Sanchez and J. Usaola, “Sipreólico - a wind power prediction system based on flexible combination of dynamic models. application to the spanish power system,” in Proceedings of the 2002WorldWind Energy Conference, Berlin, Germany, June 2002.

[66] J. Parkes and A. Tindal, “Forecasting short term wind farm production in complex terrain,” in Proceedings of the 2004 European Wind Energy Conference, EWEC’04, London, U.K., Nov. 2004. [Online]. Available: http://www.2004ewec.info/files/23_1400_jeremyparkes_01.pdf

[67] P. Louka, G. Galanis, N. Siebert, G. Kariniotakis, P. Katsafados, G. Kallos, and I. Pytharoulis, “Improvements in wind speed forecasts for wind power prediction purposes using kalman filtering,” in CD-Rom Proceedings of the CMMSE 2005, Alicante, Spain, June 2005.

[68] M. Lange, “On the uncertainty of wind power predictions. analysis of the forecast accuracy and statistical distribution of errors,” Journal of Solar Energy Engineering- Transactioncs of the ASME, vol. 127, no. 2, pp. 177–184,May 2005.

[69] A. Luig, S. Bofinger, and H. Beyer, “Analysis of confidence intervals for the prediction of regional wind power output,” in Proceedings of the 2001 European Wind Energy Conference, EWEC’01, Copenhagen, Denmark, June 2001, pp. 725–728.

[70] H. A. Nielsen, T. S. Nielsen, and H. Madsen, “Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts,” in Proceedings of the 2004 European Wind Energy Conference, EWEC’04, Scientific Track, London, United Kingdom„ Nov. 2004, pp. 34 ˝ U–38.

[71] J. B. Bremnes, “Probabilistic wind power forecasts using local quantile regression,” Wind Energy, vol. 7, no. 1, pp. 47–54, 2004. [Online]. Available: http://dx.doi.org/10.1002/we.107

[72] P. Pinson and G. Kariniotakis, “On-line assessment of prediction risk for wind power production forecasts,” in Proceedings of the 2003 European Wind Energy Conference, EWEC’03, Madrid, Spain, June 2003.

[73] G. Giebel, J. Badger, L. Landberg, H. A. Nielsen, T. S. Nielsen, H. Madsen, H. Sattler, K.andFeddersen, H. Vedel, J. Tøfting, L. Kruse, and L. Voulund, “Wind power prediction using ensembles,” Risø National Laboratory, Roskilde, Denmark, Research Report Risø-R-1527(EN), Sept. 2005. [Online]. Available: http://www.risoe.dk/rispubl/VEA/veapdf/ris-r-1527.pdf

[74] H. A. Nielsen, H. Nielsen, T. S.and Madsen, and K. Sattler, “Wind power ensemble forecasting,” in CD-Proceedings of the 2004 Global Windpower Conference, Chicago, Illinois (USA), Mar. 2004.

[75] S. Haanpää, S. Lehtonen, L. Peltonen, and E. Talockaite, Impacts of winter storm Gudrun of 7th ˝U 9th January 2005 and measures taken in Baltic Sea Region. Astra Project, 2006, report. [Online]. Available: http://www.astra-project.org/cms/sites/download/ASTRA_WSS_report_final.pdf

[76] M. R. Milligan, A. H. Miller, and F. Chapman, “Estimating the economic value of wind forecasting to utilities,” National Renewable Energy Laboratory, Golden, Colorado (U.S.), Research Report NREL/TP-441-7803, May 1995. [Online]. Available: http://www.nrel.gov/docs/legosti/old/7803.pdf

[77] B. Sørensen and P. Meibom, “Can wind power be sold in a deregulated electricity market?” in Proceedings of the 1999 EuropeanWind Energy Conference, EWEC’99, Nice, France,Mar. 1999, pp. 375–378.

[78] A. Fabbri, T. Gomez San Roman, J. Rivier Abbad, and V. Mendez Quezada, “Assessment of the cost associated with wind generation prediction errors in a liberalized electricity market,” Power Systems, IEEE Transactions on, vol. 20, no. 3, pp. 1440–1446, 2005.

[79] S. Bofinger, A. Luig, and H. G. Beyer, “Qualification of wind power forecasts,” in CDProceedings of the GlobalWind Power Conference, Paris, France, Apr. 2002.

[80] P. Pinson, C. Chevallier, and G. Kariniotakis, “Optimizing benefits from wind power participation in electricity markets using advanced tools for wind power forecasting and uncertainty assessment,” in Proceedings of the 2004 European Wind Energy Conference, EWEC’04, London, U.K., Nov. 2004. [Online]. Available: http://www.2004ewec.info/files/23_1400_pierrepinson_01.pdf

[81] P. Pinson, C. Chevallier, and N. Kariniotakis, George, “Trading wind generation with shorttermprobabilistic forecasts of wind power,” IEEE Transactions on Power Systems, vol. 22, no. 3, pp. 1148–1156, Aug. 2007.

[82] P. Pinson and G. Kariniotakis, “On-line adaptation of confidence intervals based on weather stability for wind power forecasting,” in CD-Proceeding of the 2004 Global Wind Windpower Conference, Chicago, Illinois (U.S.),Mar. 2004.

[83] U. Focken, M. Lange, and H.-P. Waldl, “Reduction of wind power prediction error by spatial smoothing effects,” in Proceedings of the 2001 European Wind Energy Association Conference EWEC’01, Copenhagen, Denmark, 2-6 July 2001, pp. 822–825.

[84] T. S. Nielsen, H. Madsen, H. A. Nielsen, L. Landberg, and G. Giebel, “Prediction of regional wind power,” in Proceeding of the 2002 Global Windpower Conference, Paris, France, April 2002.

[85] B. Ernst, K. Rohrig, P. Schorn, and H. Regber, “Managing 3000 mw wind power in a transmission system operation centres,” in Proceedings of the 2001 European Wind Energy Association Conference EWEC’01, Copenhagen, Denmark, 2-6 July 2001, pp. 890–893.

[86] K. Rohrig, B. Ernst, M. Hoppe-Kilpper, and F. Schlögl, “Online-monitoring and prediction of wind power in german transmission system operation centres,” in Proceeding WWEC 2003 - WorldWind Energy Conference, Cape Town, South Africa, November 2003. [Online]. Available: http://www.iset.uni-kassel.de/abt/FB-I/publication/03-11-01_WWEC2003.pdf

[87] S. Lang, J. Möhrlen, J. Jørgensen, B. O. Gallachóir, and E. McKeogh, “Aggregate forecasting of wind generation on the irish grid using a multi-scheme ensemble prediction system,” in Proceedings, Renewable Energy in Maritime Island Climates, 2nd Conference, Dublin, Ireland, April 2006.

[88] M. Lange and U. Focken, “State-of-the-art in wind power prediction in germany and international developments,” in Proceedings of the Second Workshop of International Feed-In Cooperation, Berlin, Dec. 2005. [Online]. Available: http://www.energymeteo.de/de/media/fic_eeg_article.pdf

[89] A. Yamaguchi, T. Ishihara, K. Sakai, T.Ogawa, and Y. Fujino, “A physical-statistical approach for the regional power forecasting,” in Proceedings of the 2007 EuropeanWind Energy Conference, EWEC’07,Milano, Italy,May 2007.

[90] T. Ishihara, A. Yamaguchi, T. Ogawa, K. Sakai, and Y. Fujino, “An upscaling approach for the regional wind power forecasting,” in Proceedings of the 2007 EuropeanWind Energy Conference, EWEC’07,Milano, Italy,May 2007.

[91] T. S. Nielsen, “Online prediction and control in nonlinear stochastic systems,” Ph.D. dissertation, Department ofMathematicalModelling, Technical University of Denmark, 2002.

[92] T. S. Nielsen and H. A. Nielsen, “Using meteorological forecasts in on-line predictions of wind power. chapter 5: Estimation methods,” 1999, iSBN: 87-90707-18-4. [Online]. Available: http://www2.imm.dtu.dk/pubdb/p.php?1706

[93] L. v. Bremen, N. Saleck, and D. Heinemann, “Enhanced regional forecasting considering single wind farm distribution for upscaling,” Journal of Physics: Conference Series, vol. 75, Aug. 2007. [Online]. Available: http://stacks.iop.org/1742-6596/75/012040

[94] G. Giebel, “On the benefits of distributed generation of wind energy in europe,” Ph.D. dissertation, Carl von Ossietzky Universität, Oldenburg, Germany, 2000.

[95] “London array project website,” Aug. 2006. [Online]. Available: http://www.londonarray.com

[96] A. Sfetsos and C. Siriopoulos, “Time series forecasting of averaged data with efficient use of information,” IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, vol. 35, no. 5, pp. 738–745, Sept. 2005.

[97] A. Papoulis, Probability, Random Variables, and Stochastic Processes, 3rd ed., ser. Electrical & Electronic Engineering Series. New York, NY, USA:McGraw-Hill, 1991.

[98] L. Balea, N. Siebert, G. Kariniotakis, and E. Peirano, “Quantification of capacity credit and reserve requirements from the large-scale integration of wind energy in the french power system,” in CD-Proceedings of the 2004 Global Windpower Conference, Chicago, Illinois (U.S.), Mar. 2004.

[99] R. M. Gray, Entropy and Information Theory. New York, NY, USA: Springer-Verlag, 1990.

[100] D.W. Scott,Multivariate Density Estimation, Theory, Practice, and Visialization, ser. Probability and Mathematical Statistics. New York: Wiley-Interscience, 1992, iSBN: 0-471-54770-0.

[101] B. Bonnlander, “Nonparametric selection of input variables for connectionist learning,” Ph.D. dissertation, University of Colorado Department of Computer Science, 1996.

[102] European Wind Energy Association, “European capacity map 2006,” 2006. [Online]. Available: http://www.ewea.org/fileadmin/ewea_documents/documents/publications/statistics/070129_Wind_map_2006.pdf

[103] V.Miranda, C. Cerqueira, and C.Monteiro, “Training a fis with epso under an entropy criterion for wind power prediction,” in On-line proceedings of the 9th International Conference on Probabilistic Methods Applied to Power Systems, Stockholm, Sweden, June 2006. [Online]. Available: http://www.congrex.se/pmaps/pdf/1.3/1.3_miranda_v.pdf

[104] H. Holttinen, P. Saarikivi, S. Repo, J. Ikäheimo, and G. Koreneff, “Prediction error and balancing costs for wind power production in finland,” in Proceedings of the Sixth International Workshop on Large-Scale Integration of Wind Power and Transmission Networks for Offshore Wind Famrs, R. L. Hendriks, B. C. Ummels, and T. Ackermann, Eds., Delft, The Netherlands, Oct. 2006, pp. 113–120.

[105] A. Woyte, G. Palmers, and L. Dewilde, “Balancing costs for large wind farms: The influence of short-term forecasting and the regulatory framework,” in Proceedings of the Sixth InternationalWorkshop on Large-Scale Integration ofWind Power and Transmission Networks for Offshore Wind Famrs, R. L. Hendriks, B. C. Ummels, and T. Ackermann, Eds., Delft, The Netherlands, Oct. 2006, pp. 121–126.

[106] V. N. Vapnik, The nature of statistical learning theory, 2nd ed., ser. Statistics for Engineering and Information Science. New York, NY, USA: Springer-Verlag New York, Inc., 1999.

[107] F. Rosenblatt, Principles of neurodynamics: Perceptron and theory of brain mechanisms. Washington D.C: Spartan Books, 1962.

[108] V. N. Vapnik, Estimation of Dependencies Based on Empirical Data. New York: Springer, 1982.

[109] V. N. Vapnik and A. J. Chervonenkis, “The necessary and sufficient conditions for consistency of the method of empirical risk minimization,” Pattern Recognition and Image Analysis, vol. 1, no. 3, pp. 284–305, 1991.

[110] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” in COLT ’92: Proceedings of the fifth annual workshop on Computational learning theory. New York, NY, USA: ACM Press, 1992, pp. 144–152.

[111] Y. LeCun, “Une procédure d’apprentissage pour réseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks),” in Proceedings of Cognitiva 85, Paris, France, 1985, pp. 599–604. [Online]. Available: http://yann.lecun.com/exdb/publis/index.html

[112] D. B. Parker, “Learning-logic,” MIT Center for Computational Research in Economics and Management Science, Cambridge, MA, TR-47, 1985.

[113] L. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338–353, June 1965. [Online]. Available: http://www.sciencedirect.com/science/article/B7MFM-4DX43MN-W3/2/f244f7a33f31015e819042700cd83047

[114] V. Kecman and B.-M. Pfeiffer, “Exploiting the structural equivalence of learning fuzzy systems and radial basis function neural networks,” in Proceedings of the Second European Congress on Intelligent Techniques and Soft Computing EUFIT-94, Aachen, Gemany, vol. 1, 1994, pp. 58–66.

[115] S. Makridakis and M. Hibon, “The m3-competition: results, conclusions and implications,” International Journal of Forecasting, vol. 16, no. 4, pp. 451–476, 2000. [Online]. Available: http://www.sciencedirect.com/science/article/B6V92-41J6944-3/2/77108ea44b47436e4527d06abc3a8ac5

[116] A. J. Koning, P. H. Franses, M. Hibon, and H. Stekler, “The m3 competition: Statistical tests of the results,” International Journal of Forecasting, vol. 21, no. 3, pp. 397–409, 2005. [Online]. Available: http://www.sciencedirect.com/science/article/B6V92-4F011CS-1/2/53b7026849c6c1659a592a5451b122eb

[117] R.Wang, V. Storey, and C. Firth, “A framework for analysis of data quality research,” Knowledge and Data Engineering, IEEE Transactions on, vol. 7, no. 4, pp. 623–640, 1995.

[118] Y. Wand and R. Y. Wang, “Anchoring data quality dimensions in ontological foundations,” Commun. ACM, vol. 39, no. 11, pp. 86–95, 1996.

[119] R. E. Bellman, Adaptive Control Processes: AGuided Tour. Princeton, NJ: PrincetonUniverssity Press, 1961.

[120] P. L. Meyer, Probabilidade: Aplicações à Estatística, 2nd ed. Rio de Janeiro, Brasil: Livros Técnicos e Cientìficos Editora, 1983.

[121] J. R. Quinlan, “Induction of decision trees,” Machine Learning, vol. 1, no. 1, pp. 81–106, Mar. 1986. [Online]. Available: http://dx.doi.org/10.1007/BF00116251

[122] P. Langley,W. Iba, and K. Thompson, “An analysis of bayesian classifiers,” in Proceedings of the 10th National Conference on Artificial Intelligence,W. R. Swartout, Ed. San Jose, CA: The AAAI Press / The MIT Press, July 12-16 1992, pp. 223–228.

[123] N. Friedman,D.Geiger, and M.Goldszmidt, “Bayesian network classifiers,”Machine Learning, vol. 29, no. 2, pp. 131–163, Nov. 1997. [Online]. Available: http://dx.doi.org/10.1023/A:1007465528199

[124] T. S. Nielsen, H. Madsen, H. A. Nielsen, P. Pinson, G. Kariniotakis, N. Siebert, I. Martí, M. Lange, U. Focken, L. von Bremen, P. Louka, G. Kallos, and G. Galanis, “Short-term wind power forecasting using advanced statistical methods,” in Proceedings of the 2006 European Wind Energy Conference, EWEC’06, Athens, Greece, 2006. [Online]. Available: http://www.ewec2006proceedings.info/index.php

[125] I. Sánchez, “Short-term prediction of wind energy production,” International Journal of Forecasting, vol. 22, no. 1, pp. 43–56, 2006. [Online]. Available: http://www.sciencedirect.com/science/article/B6V92-4HDP6VM-1/2/0f5ac6ae7950992b63e41d2dfaa2d49a

[126] C. Peck, A. Dhawan, and C. Meyer, “Genetic algorithm based input selection for a neural network function approximator with applications to ssme health monitoring,” in IEEE International Conference on Neural Networks, 1993., vol. 2, San Francisco, CA, 1993, pp. 1115–1122.

[127] T. Chow and D. Huang, “Estimating optimal feature subsets using efficient estimation of highdimensional mutual information,” Neural Networks, IEEE Transactions on, vol. 16, no. 1, pp. 213–224, 2005.

[128] D. Paravan, T. Stokelj, and R. Golob, “Selecting input variables for hpp reservoir water inflow forecasting using mutual information,” in Proceedings of the 2001 IEEE Porto Power Tech Conference, vol. 2, Porto, Portugal, Sept. 2001.

[129] I. Guyon and A. Elisseeff, “An introduction to variable and feature selection,” Journal of Machine Learning Research, vol. 3, pp. 1157–1182,Mar. 2003.

[130] R. Kohavi and G. H. John, “Wrappers for feature subset selection,” Artificial Intelligence, vol. 97, no. 1-2, pp. 273–324, Dec. 1997.

[131] A. Blum and R. L. Rivest, “Training a 3-node neural network is NP-complete,”NeuralNetworks, vol. 5, no. 1, pp. 117–127, 1992.

[132] D. M. Chickering, D. Geiger, and D. Heckerman, “Learning Bayesian Networks is NP-Hard,” Microsoft Research, Advanced Technology Division, Microsoft Corporation, One Microsoft Way, Redmond,WA 98052, Tech. Rep. MSR-TR-94-17, Nov. 1994.

[133] A. Blum and P. Langley, “Selection of relevant features and examples in machine learning,” Artificial Intelligence, vol. 97, no. 1-2, pp. 245–271, Dec. 1997.

[134] M. Hall, “Correlation-based feature selection for machine learning,” Ph.D. dissertation, Waikato University, Department of Computer Science., Hamilton, NZ, Apr. 1999. [Online]. Available: citeseer.ist.psu.edu/hall99correlationbased.html

[135] R. Battiti, “Using mutual information for selecting features in supervised neural net learning,” Neural Networks, IEEE Transactions on, vol. 5, no. 4, pp. 537–550, 1994.

[136] D. A. Bell and H. Wang, “A formalism for relevance and its application in feature subset selection,” Machine Learning, vol. 41, no. 2, pp. 175–195, Nov. 2000. [Online]. Available: http://dx.doi.org/10.1023/A:1007612503587

[137] K. Li, “A new input selection method for neural modeling of nonlinear complex systems,” in Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on, vol. 3, 2004, pp. 2018–2021 Vol.3.

[138] P. Mitra, C. Murthy, and S. Pal, “Unsupervised feature selection using feature similarity,” Pattern Analysis andMachine Intelligence, IEEE Transactions on, vol. 24, no. 3, pp. 301–312, 2002.

[139] R. Šindeláˇr and R. Babuška, “Input selection for nonlinear regression models,” IEEE Transactions on Fuzzy Systems, vol. 12, no. 5, pp. 688–696, Oct. 2004.

[140] B. V. Bonnlander and A. S. Weigend, “Selecting input variables using mutual information and nonparametric density estimation,” in Proc. of the 1994 Int. Symp. on Artificial Neural Networks (ISANN"94), Tainan, Taiwan, 1994, pp. 42–50. [Online]. Available: citeseer.ist.psu.edu/bonnlander96selecting.html

[141] K. Torkkola, “Feature extraction by non-parametric mutual information,” Journal of Machine Learning Research, vol. 3, pp. 1415–1438,Mar. 2003.

[142] A. Singhal and D. Seborg, “Clustering of multivariate time-series data,” in Proceedings of the 2002 American Control Conference., vol. 5, Anchorage, AK,May 2002, pp. 3931–3936.

[143] M.Dash and H. Liu, “Feature selection for classification,” IntelligentData Analysis, vol. 1, no. 3, pp. 131–156, 1997.

[144] M. Hall and G. Holmes, “Benchmarking attribute selection techniques for discrete class data mining,” IEEE Transactions on Knowledge and Data Engineering, vol. 15, no. 6, pp. 1437–1447, 2003.

[145] J. Juban, N. Siebert, and G. Kariniotakis, “Probabilistic short-term wind power forecasting for the optimal management of wind generation,” in Power Tech Proceedings, 2007 IEEE Lausane, Lausane, Zwitserland, July 2007.

[146] J. P.Marques de Sá, Pattern Recognition: Concepts,Methods ans Applications. Berlin: Springer Verlag, 2001.

[147] L. M. Costa and G. Kariniotakis, “A stochastic dynamic programming model for optimal use of local energy resources in a market environment,” in Power Tech Proceedings, 2007 IEEE Lausane, Lausanne, Switzerland, July 2007.

[148] R. Buizza, “Potential Forecast Skill of Ensemble Prediction and Spread and Skill Distributions of the ECMWF Ensemble Prediction System,” Monthly Weather Review, vol. 125, no. 1, pp. 99–119, 1997. [Online]. Available: http://dx.doi.org/10.1175%2F1520-0493%281997%29125%3C0099%3APFSOEP%3E2.0.CO%3B2

Table des Matières

Contents

Acknowledgments

Contents

List of Figures

List of Tables

Abbreviations, Notations andMathematical Symbols

1 Introduction

1.1 General context

1.2 Wind power forecasting

1.3 Regional wind power forecasting

1.4 Purpose of the thesis

1.5 Structure of the thesis

2 State of the Art inWind Power Forecasting

2.1 Introduction

2.2 Basic concepts

2.3 Model Performance Evaluation

2.4 Overview of state-of-the-art wind power forecasting models

2.4.1 Time seriesModels

2.4.2 PhysicalModels

2.4.3 StatisticalModels

2.4.4 Model benchmarking

2.5 Uncertainty ofWind Power Forecasts

2.6 Value ofWind Power Forecasts

2.7 Regional PredictionModels

2.8 Conclusion

3 Characterization of regional forecasting

3.1 Introduction

3.2 Defining regional wind power forecasting

3.3 Time Series Analysis of regional production

3.4 Regional production as the sum of individual productions

3.4.1 Statistical smoothing of regional production

3.4.2 Statistical relation between regional production and single wind farm productions

3.4.3 Statistical relation between regional production and numerical weather predictions

3.5 Scope of the study

3.5.1 Irish case-study

3.5.2 Danish case-study

3.6 Characterization of regional production

3.6.1 Time series analysis of regional production

3.6.2 Characterizing the statistical smoothing of regional production

3.6.3 Characterization of the relation between single wind farm productions and regional productions

3.6.4 Characterization of the relation between regional production and numerical weather forecasts

3.7 Conclusion

4 Regional ForecastingModels

4.1 Introduction

4.2 The Regional Forecasting Problem

4.3 RegionalModelling Approaches

4.4 Statistical LearningModels for Regional Forecasting

4.4.1 Fuzzy-Neural NetworkModel

4.4.2 Regressive Power CurveModel

4.5 Scope of the study

4.5.1 Validation of the RPC model for single wind farmforecasting

4.5.2 Regional Forecasting Approaches

4.5.3 Comparison of modelling approaches

4.6 Evaluation of Regional Model Performance

4.6.1 RPCModel Validation

4.6.2 Evaluation of the Direct Regional Forecasting Approach

4.6.3 Evaluation of the Cascaded Regional Forecasting

4.6.4 Evaluation of the Cluster Regional Forecasting

4.6.5 Comparison of modelling approaches

4.7 General conclusions

5 Explanatory Variable Selection

5.1 Introduction

5.2 Explanatory Variables Selection for Regional Forecasting

5.3 A Framework for Examining the Impact of Variable Subset Selection on Regional Forecasting Accuracy

5.3.1 Determining the Number of Explanatory Variables Subsets

5.3.2 The Considered Regional ForecastingModel

5.3.3 Determining the forecast performance of an explanatory variable subset

5.3.4 Variable subset characteristics

5.4 Evaluation of the Impact of Variable Subset Characteristics on Forecast Accuracy

5.4.1 Case studies

5.4.2 Results for the PowerMeasurement Subsets

5.4.3 Results for theWind Speed Forecast Subsets

5.5 Explanatory variable selection methods

5.5.1 Definitions

5.5.2 Overview of Variable SelectionMethods

5.5.3 Proposed variable selection methods for regional wind power forecasting

5.6 Evaluation of the proposed variable selection methods

5.6.1 Scope of the study

5.6.2 Results for the MIFS Algorithm

5.6.3 Results for the ClusteringMethod

5.6.4 Results for theWrapper Algorithm

5.7 Conclusions

6 General Conclusions

6.1 Overall conclusions and contribution

6.2 Perspectives

A Complementary Characterization Results

A.1 Smoothing and aggregation results for the Irish case study

B Complementary Regional Forecasting Results

B.1 Validation of the RPC model for single wind farmforecasting

B.2 Direct Approach for the Danish Case

B.3 Cluster Approach for the Irish Case

B.4 Comparison of modelling approaches

C Complementary Variable Combination Results

D Traduction en Français

D.1 Introduction

D.1.1 Contexte général

D.1.2 Prédiction de la production éolienne

D.1.3 Le prédiction de la production éolienne régionale

D.1.4 But de la thèse

D.1.5 Structure de la thèse

D.2 Conclusions générales

D.2.1 Conclusions et contribution de la thèse

D.2.2 Perspectives

D.3 Traduction des chapeaux de chapitre

D.3.1 Résumé Chapitre 2

D.3.2 Résumé Chapitre 3

D.3.3 Résumé Chapitre 4

D.3.4 Résumé Chapitre 5

Bibliography

Statistiques de consultation

Administrateurs de l'archive uniquement : éditer cet enregistrement