Space-Time Trajectories of Wind Power Generation: Parametrized Precision Matrices Under a Gaussian Copula Approach

  • Julija TastuEmail author
  • Pierre Pinson
  • Henrik Madsen
Conference paper
Part of the Lecture Notes in Statistics book series (LNS, volume 217)


Emphasis is placed on generating space-time trajectories of wind power generation, consisting of paths sampled from high-dimensional joint predictive densities, describing wind power generation at a number of contiguous locations and successive lead times. A modelling approach taking advantage of the sparsity of precision matrices is introduced for the description of the underlying space-time dependence structure. The proposed parametrization of the dependence structure accounts for important process characteristics such as lead-time-dependent conditional precisions and direction-dependent cross-correlations. Estimation is performed in a maximum likelihood framework. Based on a test case application in Denmark, with spatial dependencies over 15 areas and temporal ones for 43 hourly lead times (hence, for a dimension of n = 645), it is shown that accounting for space-time effects is crucial for generating skilful trajectories.


Lead Time Wind Power Dependence Structure Copula Function Conditional Correlation 
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.



The authors were partly supported by the EU Commission through the project SafeWind (ENK7-CT2008-213740), which is hereby acknowledged. Pierre Pinson was additionally supported by the Danish Strategic Research Council under ‘5s’–Future Electricity Markets (12-132636/DSF). The authors are grateful to, the transmission system operator in Denmark, for providing the observed power data used in this paper, and to ENFOR A/S for generating the point forecasts of wind power generation used as input. Finally, reviewers and editors are acknowledged for their comments and suggestions on an earlier version of the manuscript.


  1. 1.
    Ackermann, T., et al. (2005). Wind power in power systems. New York: Wiley.CrossRefGoogle Scholar
  2. 2.
    Bernardo, J. M. (1979). Expected information as expected utility. The Annals of Statistics, 7(3), 686–690.zbMATHMathSciNetCrossRefGoogle Scholar
  3. 3.
    Besag, J. (1974). Spatial interaction and the statistical analysis of lattice systems. Journal of the Royal Statistical Society. Series B, 36, 192–236.zbMATHMathSciNetGoogle Scholar
  4. 4.
    Bessa, R. J., Matos, M. A., Costa, I. C., Bremermann, L., Franchin, I. G., Pestana, R., Machado, N., Waldl, H. P., & Wichmann, C. (2012). Reserve setting and steady-state security assessment using wind power uncertainty forecast: A case study. IEEE Transactions on Sustainable Energy, 3, 827–836.CrossRefGoogle Scholar
  5. 5.
    Bessa, R. J., Miranda, V., Botterud, A., Zhou, Z., & Wang, J. (2012). Time-adaptive quantile-copula for wind power probabilistic forecasting. Renewable Energy, 40(1), 29–39.CrossRefGoogle Scholar
  6. 6.
    Botterud, A., Zhou, Z., Wang, J., Bessa, R. J., Keko, H., Sumaili, J., & Miranda, V. (2012). Wind power trading under uncertainty in LMP markets. IEEE Transactions on Power Systems, 27(2), 894–903.CrossRefGoogle Scholar
  7. 7.
    Botterud, A., Zhou, Z., Wang, J., Sumaili, J., Keko, H., Mendes, J., Bessa, R. J., & Miranda, V. (2013). Demand dispatch and probabilistic wind power forecasting in unit commitment and economic dispatch: A case study of Illinois. IEEE Transactions on Sustainable Energy, 4(1), 250–261.CrossRefGoogle Scholar
  8. 8.
    Bröcker, J., & Smith, L. A. (2007). Scoring probabilistic forecasts: The importance of being proper. Weather and Forecasting, 22(2), 382–388.CrossRefGoogle Scholar
  9. 9.
    Castronuovo, E. D., Sánchez, I., Usaola, J., Bessa, R., Matos, M., Costa, I. C., Bremermann, L., Lugaro, J., & Kariniotakis, G. (2013). An integrated approach for optimal coordination of wind power and hydro pumping storage. Wind Energy, 17(6), 829–852. Available online.Google Scholar
  10. 10.
    Costa, A., Crespo, A., Navarro, J., Lizcano, G., Madsen, H., & Feitosa, E. (2008). A review on the young history of the wind power short-term prediction. Renewable & Sustainable Energy Reviews, 12(6), 1725–1744.CrossRefGoogle Scholar
  11. 11.
    Diaz, G. (2013). A note on the multivariate Archimedian dependence structure in small wind generation sites. Wind Energy, 17(8), 1287–1295. Available online (doi:10.1002/we.1633).Google Scholar
  12. 12.
    Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253–263.Google Scholar
  13. 13.
    Genest, C., & Favre, A.-C. (2007). Everything you always wanted to know about copula modeling but were afraid to ask. Journal of Hydrologic Engineering, 12(4), 347–368.CrossRefGoogle Scholar
  14. 14.
    Giebel, G., Brownsword, R., Kariniotakis, G., Denhard, M., & Draxl, C. (2011). The state-of-the-art in short-term prediction of wind power–A literature overview (2nd ed.). Technical report, Technical University of Denmark.Google Scholar
  15. 15.
    Girard, R., & Allard, D. (2012). Spatio-temporal propagation of wind power prediction errors. Wind Energy, 16(7), 999–1012.CrossRefGoogle Scholar
  16. 16.
    Gneiting, T. (2008). Editorial: Probabilistic forecasting. Journal of the Royal Statistical Society: Series A, 171(2), 319–321.MathSciNetCrossRefGoogle Scholar
  17. 17.
    Gneiting, T., & Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102(477), 359–378.zbMATHMathSciNetCrossRefGoogle Scholar
  18. 18.
    Gneiting, T., Stanberry, L. I., Grimit, E. P., Held, L., & Johnson, N. A. (2008). Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds. Test, 17(2), 211–235.zbMATHMathSciNetCrossRefGoogle Scholar
  19. 19.
    Hafner, C. M., & Manner, H. (2012). Conditional prediction intervals of wind power generation. Journal of Applied Econometrics, 27(2), 269–295.MathSciNetCrossRefGoogle Scholar
  20. 20.
    Hagspiel, S., Papaemannouil, A., Schmid, M., & Andersson, G. (2012). Copula-based modeling of stochastic wind power in Europe and implications for the Swiss power grid. Applied Energy, 96, 33–44.CrossRefGoogle Scholar
  21. 21.
    Hofert, M., Mächler, M., & Mcneil, A. J. (2012). Likelihood inference for archimedean copulas in high dimensions under known margins. Journal of Multivariate Analysis, 110, 133–150.zbMATHMathSciNetCrossRefGoogle Scholar
  22. 22.
    Jeon, J., & Taylor, J. W. (2012). Using conditional kernel density estimation for wind power density forecasting. Journal of the American Statistical Association, 107(497), 66–79.zbMATHMathSciNetCrossRefGoogle Scholar
  23. 23.
    Jones, L., & Clark, C. (2011). Wind integration – A survey of global views of grid operators. In Proceedings of the 10th international workshop on large-scale integration of wind power into power systems, Aarhus.Google Scholar
  24. 24.
    Kyung, M., & Ghosh, S. K. (2010). Maximum likelihood estimation for directional conditionally autoregressive models. Journal of Statistical Planning and Inference, 140(11), 3160–3179.zbMATHMathSciNetCrossRefGoogle Scholar
  25. 25.
    Lindgren, F., Rue, H., & Lindström, J. (2011). An explicit link between gaussian fields and gaussian markov random fields: The stochastic partial differential equation approach. Journal of the Royal Statistical Society: Series B, 73(4), 423–498.zbMATHMathSciNetCrossRefGoogle Scholar
  26. 26.
    Louie, H. (2014). Evaluation of bivariate archimedean and elliptical copulas to model wind power dependency structures. Wind Energy, 17(2), 225–240.CrossRefGoogle Scholar
  27. 27.
    Madsen, H., & Thyregod, P. (2011). Introduction to general and generalized linear models. Boca Raton: Chapman & Hall/CRC.zbMATHGoogle Scholar
  28. 28.
    Möller, A., Lenkoski, A., & Thorarinsdottir, T. L. (2013). Multivariate probabilistic forecasting using bayesian model averaging and copulas. Quarterly Journal of the Royal Meteorological Society, 139, 982–991.CrossRefGoogle Scholar
  29. 29.
    Nielsen, H.Aa., Nielsen, T. S., & Madsen, H. (2011). An overview of wind power forecasts types and their use in large-scale integration of wind power. In Proceedings of the 10th international workshop on large-scale integration of wind power into power systems, Aarhus.Google Scholar
  30. 30.
    Ortega-Vazquez, M. A., & Kirschen, D. S. (2010). Assessing the impact of wind power generation on operating costs. IEEE Transactions on Smart Grid, 1(3), 295–301.CrossRefGoogle Scholar
  31. 31.
    Papaefthymiou, G., & Kurowicka, D. (2009). Using copulas for modeling stochastic dependence in power system uncertainty analysis. IEEE Transactions on Power Systems, 24(1), 40–49.CrossRefGoogle Scholar
  32. 32.
    Papavasiliou, A., & Oren, S. S. (2013). Multiarea stochastic unit commitment for high wind penetration in a transmission constrained network. Operations Research, 61, 578–592.zbMATHMathSciNetCrossRefGoogle Scholar
  33. 33.
    Pinson, P. (2013). Wind energy: Forecasting challenges for its optimal management. Statistical Science, 28(4), 564–585.MathSciNetCrossRefGoogle Scholar
  34. 34.
    Pinson, P., & Girard, R. (2012). Evaluating the quality of scenarios of short-term wind power generation. Applied Energy, 96, 12–20.CrossRefGoogle Scholar
  35. 35.
    Pinson, P., & Kariniotakis, G. N. (2010). Conditional prediction intervals of wind power generation. IEEE Transactions on Power Systems, 25(4), 1845–1856.CrossRefGoogle Scholar
  36. 36.
    Pinson, P., Madsen, H., Aa Nielsen, H., Papaefthymiou, G., & Klöckl, B. (2009). From probabilistic forecasts to statistical scenarios of short-term wind power production. Wind Energy, 12(1), 51–62.CrossRefGoogle Scholar
  37. 37.
    Pinson, P., Nielsen, H. A., Møller, J. K., Madsen, H., & Kariniotakis, G. N. (2007). Non-parametric probabilistic forecasts of wind power: Required properties and evaluation. Wind Energy, 10(6), 497–516.CrossRefGoogle Scholar
  38. 38.
    Pinson, P., & Tastu, J. (2013). Discrimination ability of the Energy score. Technical report, Technical University of Denmark.Google Scholar
  39. 39.
    Rue, H., & Held, L. (2005). Gaussian Markov random fields: Theory and applications, vol. 104. Boca Raton: Chapman & Hall.Google Scholar
  40. 40.
    Rue, H., & Tjelmeland, H. (2002). Fitting gaussian markov random fields to gaussian fields. Scandinavian Journal of Statistics, 29(1), 31–49.zbMATHMathSciNetCrossRefGoogle Scholar
  41. 41.
    Simpson, D., Lindgren, F., & Rue, H. (2012). In order to make spatial statistics computationally feasible, we need to forget about the covariance function. Environmetrics, 23(1), 65–74.MathSciNetCrossRefGoogle Scholar
  42. 42.
    Sklar, M. (1959). Fonctions de répartition à n dimensions et leurs marges. Université Paris 8.Google Scholar
  43. 43.
    Tastu, J., Pinson, P., & Madsen, H. (2010). Multivariate conditional parametric models for a spatiotemporal analysis of short-term wind power forecast errors. In Scientific proceedings of the European wind energy conference, Warsaw (pp. 77–81).Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Siemens Wind PowerBallerupDanmark
  2. 2.Technical University of DenmarkLyngbyDanmark
  3. 3.Technical University of DenmarkLyngbyDanmark

Personalised recommendations