Estimation of the uncertainty in wind power forecasting

Wind power experiences a tremendous development in Europe. Though, the intermittence of wind generation causes difficulties in the management of power systems. Moreover, in the context of the deregulation of electricity markets, wind energy is penalized by its intermittent nature. It is recognized today that the forecasting of wind power for horizons up to 2/3-day ahead eases the integration of wind generation. Wind power forecasts are traditionally provided in the form of point predictions, which correspond to the most-likely power production for a given horizon. That sole information is not sufficient for developing optimal management or trading strategies. Therefore, we investigate on possible ways for estimating the uncertainty of wind power forecasts. The characteristics of the prediction uncertainty are described by a thorough study of the performance of some of the state-of-the-art approaches, and by underlining the influence of some variables e.g. level of predicted power on distributions of prediction errors. Then, a generic method for the estimation of prediction intervals is introduced. This statistical method is non-parametric and utilizes fuzzy logic concepts for integrating expertise on the prediction uncertainty characteristics. By estimating several prediction intervals at once, one obtains predictive distributions of wind power output. The proposed method is evaluated in terms of its reliability, sharpness and resolution. In parallel, we explore the potential use of ensemble predictions for skill forecasting. Wind power ensemble forecasts are obtained either by converting meteorological ensembles (from ECMWF and NCEP) to power or by applying a poor man's temporal approach. A proposal for the definition of prediction risk indices is given, reflecting the disagreement between ensemble members over a set of successive look-ahead times. Such risk indices may comprise a more comprehensive signal on the expected level of uncertainty in an operational environment. A probabilistic relation between classes of risk indices and the level of forecast error is shown. In a final part, the trading application is considered for demonstrating the value of uncertainty estimation when predicting wind generation. It is explained how to integrate that uncertainty information in a decision-making process accounting for the sensitivity of end-users to regulation costs. The benefits of having a probabilistic view of wind power forecasting are clearly shown.

[1]  E. Lorenz.  A study of the predictability of a 28-variable atmospheric model , 1965 .

[2]  J. J. Reeves.  Bootstrap prediction intervals for ARCH models , 2005 .

[3]  Luis A. Escobar,et al.  Statistical Intervals: A Guide for Practitioners , 1991 .

[4]  Reinhard Madlener,et al.  Power exchange spot market trading in Europe: theoretical considerations and empirical evidence , 2002 .

[5]  Pierre Pinson,et al.  On‐line assessment of prediction risk for wind power production forecasts , 2003 .

[6]  Yu Erkeng,et al.  Short-term electrical load forecasting using least squares support vector machines , 2002, Proceedings. International Conference on Power System Technology.

[7]  Hannele Holttinen,et al.  Power System Requirements for Wind Power , 2005 .

[8]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[9]  Leonard A. Smith,et al.  Evaluating Probabilistic Forecasts Using Information Theory , 2002 .

[10]  J. T. Hwang,et al.  Prediction Intervals for Artificial Neural Networks , 1997 .

[11]  Georges Kariniotakis,et al.  Short-term wind power prediction for offshore wind farms Evaluation of Fuzzy-Neural network based models , 2004 .

[12]  Lennart Siider,et al.  Reserve Margin Planning in a Wind-Hydro-Thermal Power System , 1993 .

[13]  Poul Erik Morthorst,et al.  Wind power and the conditions at a liberalized power market , 2003 .

[14]  P. Pinson,et al.  Uncertainty of short-term wind power forecasts a methodology for on-line assessment , 2004, 2004 International Conference on Probabilistic Methods Applied to Power Systems.

[15]  R. Buizza,et al.  A Comparison of the ECMWF, MSC, and NCEP Global Ensemble Prediction Systems , 2005 .

[16]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[17]  Lars Landberg,et al.  Short-term prediction of the power production from wind farms , 1999 .

[18]  L. Soder,et al.  Wind power integration in power systems with bottleneck problems , 2003, 2003 IEEE Bologna Power Tech Conference Proceedings,.

[19]  Leonard A. Smith,et al.  Using medium-range weather forcasts to improve the value of wind energy production , 2003 .

[20]  T. Evgeniou,et al.  To combine or not to combine: selecting among forecasts and their combinations , 2005 .

[21]  Stanley G. Benjamin,et al.  6 WIND ENERGY FORECASTS AND ENSEMBLE UNCERTAINTY FROM THE RUC , .

[22]  P. L. Houtekamer,et al.  Global and Local Skill Forecasts , 1993 .

[23]  Christian Genest,et al.  Allocating the weights in the linear opinion pool , 1990 .

[24]  L. S. Moulin,et al.  Confidence intervals for neural network based short-term load forecasting , 2000 .

[25]  Regine Belhomme.  Wind Power Developments in France , 2002, IEEE Power Engineering Review.

[26]  Ross N. Hoffman,et al.  Lagged average forecasting, an alternative to Monte Carlo forecasting , 1983 .

[27]  C. Ziehmann,et al.  Skill prediction of local weather forecasts based on the ECMWF ensemble , 2001 .

[28]  Henrik Madsen,et al.  Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts , 2006 .

[29]  L. J. Vermeera,et al.  Wind turbine wake aerodynamics , 2003 .

[30]  R. Buizza,et al.  Using weather ensemble predictions in electricity demand forecasting , 2003 .

[31]  G. Galanisa,et al.  Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering , 2006 .

[32]  W. R. Hargraves,et al.  Methods for Estimating Wind Speed Frequency Distributions. , 1978 .

[33]  Detlev Heinemann,et al.  Relating the uncertainty of short-term wind speed predictions to meteorological situations with methods from synoptic climatology , 2004 .

[34]  Poul Erik Morthorst,et al.  Wind power and a liberalised North European electricity exchange , 1999 .

[35]  S. Roberts,et al.  Confidence Intervals and Prediction Intervals for Feed-Forward Neural Networks , 2001 .

[36]  Spyros Makridakis,et al.  Confidence intervals: An empirical investigation of the series in the M-competition , 1987 .

[37]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control , 1994 .

[38]  J. Contreras,et al.  Forecasting electricity prices for a day-ahead pool-based electric energy market , 2005 .

[39]  Rebecca J. Barthelmie,et al.  Analytical modelling of large wind farm clusters , 2004 .

[40]  Alexander Boogert,et al.  On the effectiveness of the anti-gaming policy between the day-ahead and real-time electricity markets in The Netherlands , 2005 .

[41]  S. Enomoto.  PREDICTION OF POWER OUTPUT FROM WIND FARM USING LOCAL METEOROLOGICAL ANALYSIS , 2001 .

[42]  Paul J. Roebber.  Variability in Successive Operational Model Forecasts of Maritime Cyclogenesis , 1990 .

[43]  A. Raftery,et al.  Probabilistic forecasts, calibration and sharpness , 2007 .

[44]  Craig B. Borkowf,et al.  Time-Series Forecasting , 2002, Technometrics.

[45]  Kevin J. Brundage.  Wind Energy Forecasting Using Time Lagged Ensembles , 2005 .

[46]  Andrew F. Loughe,et al.  The Relationship between Ensemble Spread and Ensemble Mean Skill , 1998 .

[47]  Yuejian Zhu,et al.  The Use of Ensembles to Identify Forecasts with Small and Large Uncertainty , 2001 .

[48]  Athanasios Sfetsos,et al.  A comparison of various forecasting techniques applied to mean hourly wind speed time series , 2000 .

[49]  S. Dubey,et al.  Normal and weibull distributions , 1967 .

[50]  E. F. McCarthy.  Wind speed forecasting in the central California wind resource area , 1997 .

[51]  Georges Kariniotakis,et al.  Evaluation of the MORE-CARE wind power prediction platform. Perfrmance of the fuzzy logic based models , 2003 .

[52]  Julio Hernández,et al.  Survey of modelling methods for wind turbine wakes and wind farms , 1999 .

[53]  Adrian E. Raftery,et al.  Weather Forecasting with Ensemble Methods , 2005, Science.

[54]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[55]  R. D. Veaux,et al.  Prediction intervals for neural networks via nonlinear regression , 1998 .

[56]  Ulfar Linnet,et al.  Tools supporting wind energy trade in deregulated markets , 2005 .

[57]  R. L. Winkler.  A Decision-Theoretic Approach to Interval Estimation , 1972 .

[58]  Refractor.  Uncertainty , 2001, The Lancet.

[59]  Joachim Peinke,et al.  A phenomenological model for the dynamic response of wind turbines to turbulent wind , 2004 .

[60]  G. Giebel,et al.  ZEPHYR – THE PREDICTION MODELS , 2022 .

[61]  Norman R. Swanson,et al.  Forecasting economic time series using flexible versus fixed specification and linear versus nonlinear econometric models , 1997 .

[62]  Gregor Giebel,et al.  State-of-the-Art on Methods and Software Tools for Short-Term Prediction of Wind Energy Production , 2003 .

[63]  Kristin P. Bennett,et al.  Support vector machines: hype or hallelujah? , 2000, SKDD.

[64]  M. O'Malley,et al.  System operation with a significant wind power penetration , 2004, IEEE Power Engineering Society General Meeting, 2004..

[65]  B. Hobbs,et al.  Analysis of the value for unit commitment of improved load forecasts , 1999 .

[66]  A. H. Murphy,et al.  Time Series Models to Simulate and Forecast Wind Speed and Wind Power , 1984 .

[67]  Georges Kariniotakis,et al.  Evaluation of advanced wind power and load forecasting methods for the optimal management of isolated power systems , 1999 .

[68]  Lawrence L. Takacs,et al.  A Two-Step Scheme for the Advection Equation with Minimized Dissipation and Dispersion Errors , 1985 .

[69]  Siu Hung Cheung,et al.  Multiple forecasts with autoregressive time series models: case studies , 2004, Math. Comput. Simul..

[70]  Kenneth F. Wallis,et al.  Forecast Uncertainty, Its Representation And Evaluation , 2008 .

[71]  Michael P. Clements,et al.  A companion to economic forecasting , 2004 .

[72]  Georges Kariniotakis,et al.  An advanced On-line Wind Resource Prediction system for the optimal management of wind park , 2002 .

[73]  L. Soder,et al.  Generation of regulating power price scenarios , 2005, 2004 International Conference on Probabilistic Methods Applied to Power Systems.

[74]  Georges Kariniotakis,et al.  Uncertainty and Prediction Risk Assessment of short-term wind power forecasts , 2004 .

[75]  A. Fabbri,et al.  Assessment of the cost associated with wind generation prediction errors in a liberalized electricity market , 2005, IEEE Transactions on Power Systems.

[76]  Georges Kariniotakis,et al.  Forecasting of regional wind generation by a dynamic fuzzy-neural networks based upscaling approach , 2003 .

[77]  Michael P. Clements,et al.  Bootstrapping prediction intervals for autoregressive models , 2001 .

[78]  M. Lange,et al.  Forecasting offshore wind speeds above the North Sea , 2005 .

[79]  C. Leith.  Theoretical Skill of Monte Carlo Forecasts , 1974 .

[80]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[81]  M. O'Malley,et al.  A new approach to quantify reserve demand in systems with significant installed wind capacity , 2005, IEEE Transactions on Power Systems.

[82]  Yozo Fujino,et al.  Experimental study of the wind flow in a coastal region of Japan , 2003 .

[83]  M. Stone.  The Opinion Pool , 1961 .

[84]  M. Lange.  On the Uncertainty of Wind Power Predictions—Analysis of the Forecast Accuracy and Statistical Distribution of Errors , 2005 .

[85]  George Stavrakakis,et al.  Wind power forecasting using advanced neural networks models , 1996 .

[86]  Anne B. Koehler,et al.  An inappropriate prediction interval , 1990 .

[87]  Wolfgang Schmidt,et al.  Wake effects in a linear wind farm , 1994 .

[88]  Charles A. Doswell,et al.  A Comparison of Measures-Oriented and Distributions-Oriented Approaches to Forecast Verification , 1996 .

[89]  C. Rossby.  Relation between variations in the intensity of the zonal circulation of the atmosphere and the displacements of the semi-permanent centers of action , 1939 .

[90]  J. Højstrup,et al.  A Simple Model for Cluster Efficiency , 1987 .

[91]  J.P. Barton,et al.  Energy storage and its use with intermittent renewable energy , 2004, IEEE Transactions on Energy Conversion.

[92]  Magne Jørgensen,et al.  An effort prediction interval approach based on the empirical distribution of previous estimation accuracy , 2003, Inf. Softw. Technol..

[93]  Pierre Pinson,et al.  The state of the art in short term prediction of wind power - from an offshore perspective , 2004 .

[94]  John Bjørnar Bremnes,et al.  Probabilistic wind power forecasts using local quantile regression , 2004 .

[95]  Francesco Lisi,et al.  Interval prediction for chaotic time series , 2001 .

[96]  M. Lange,et al.  Previento-A Wind Power Prediction System with an Innovative Upscaling Algorithm , 2001 .

[97]  Rob J. Hyndman,et al.  Highest‐density forecast regions for nonlinear and non‐normal time series models , 1995 .

[98]  Tom A. B. Snijders.  On Cross-Validation for Predictor Evaluation in Time Series , 1988 .

[99]  C. Moehrlen.  Uncertainty in wind energy forecasting , 2004 .

[100]  J. Usaola,et al.  Benefits for Wind Energy in Electricity Markets from Using Short Term Wind Power Prediction Tools; A Simulation Study , 2004 .

[101]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[102]  T. Ackermann,et al.  World-wide offshore wind potential and European projects , 2001, 2001 Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.01CH37262).

[103]  Henrik Madsen,et al.  The Zephyr project - The next generation prediction system (poster) , 2001 .

[104]  Magnus Korpaas,et al.  Operation and sizing of energy storage for wind power plants in a market system , 2003 .

[105]  E. Grimit,et al.  Initial Results of a Mesoscale Short-Range Ensemble Forecasting System over the Pacific Northwest , 2002 .

[106]  Henrik Madsen,et al.  Analysis of the results of an on-line wind power quantile forecasting system , 2006 .

[107]  Henrik Madsen,et al.  Prediction models in complex terrain. , 2001 .

[108]  F. Molteni,et al.  The ECMWF Ensemble Prediction System: Methodology and validation , 1996 .

[109]  A. H. Murphy,et al.  Skill Scores and Correlation Coefficients in Model Verification , 1989 .

[110]  Padraig Cunningham,et al.  Confidence and prediction intervals for neural network ensembles , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[111]  Georges Kariniotakis,et al.  Optimizing Benefits from wind power participation in electricity market using advanced tools for wind power forecasting and uncertainty assessment , 2004 .

[112]  Tom Heskes,et al.  Practical Confidence and Prediction Intervals , 1996, NIPS.

[113]  Karsten Neuhoff,et al.  Comparison of feed-in tariff, quota and auction mechanisms to support wind power development , 2008 .

[114]  H. Madsen,et al.  PREDICTION OF REGIONAL WIND POWER , 2022 .

[115]  Erik Lundtang Petersen,et al.  The European Wind Atlas , 1985 .

[116]  Nikola K. Kasabov,et al.  DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction , 2002, IEEE Trans. Fuzzy Syst..

[117]  Lars Landberg,et al.  Short-term prediction of local wind conditions , 1994 .

[118]  Arthouros Zervos,et al.  Developing wind energy to meet the Kyoto targets in the European union , 2003 .

[119]  H. Aa,et al.  PREDICTION OF WIND POWER USING TIME-VARYING COEFFICIENT-FUNCTIONS , 2002 .

[120]  Sven-Erik Thor,et al.  Long‐term research and development needs for wind energy for the time frame 2000–2020 , 2002 .

[121]  Kaplan,et al.  ‘Combining Probability Distributions from Experts in Risk Analysis’ , 2000, Risk analysis : an official publication of the Society for Risk Analysis.

[122]  Derek W. Bunn,et al.  Investigating improvements in the accuracy of prediction intervals for combinations of forecasts: A simulation study , 1999 .

[123]  H. Holttinen.  Optimal electricity market for wind power , 2004 .

[124]  B. Lange,et al.  Importance of thermal effects and sea surface roughness for offshore wind resource assessment , 2004 .

[125]  Vladimiro Miranda,et al.  Probabilistic choice vs. risk analysis-conflicts and synthesis in power system planning , 1997 .

[126]  W.J. Lee,et al.  An integration of ANN wind power estimation into UC considering the forecasting uncertainty , 2005, IEEE Systems Technical Conference on Industrial and Commercial Power 2005..

[127]  mith,et al.  Evaluating Probabilistic Forecasts Using Information Theory , 2002 .

[128]  Lars Landberg,et al.  A mathematical look at a physical power prediction model , 1998 .

[129]  Matteo Grigoletto,et al.  Bootstrap prediction intervals for autoregressions: some alternatives , 1998 .

[130]  Thomas R. Stewart,et al.  Uncertainty, Judgment, and Error in Prediction , 2000 .

[131]  T. Palmer.  Predicting uncertainty in forecasts of weather and climate , 2000 .

[132]  T. Palmer,et al.  Stochastic representation of model uncertainties in the ECMWF ensemble prediction system , 2007 .

[133]  Ismael Sánchez,et al.  Short-term prediction of wind energy production , 2006 .

[134]  P. Lundsager,et al.  Integration of wind power in the power system , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[135]  P. Pinson,et al.  What performance can be expected by short-term wind power prediction models depending on site characteristics? , 2004 .

[136]  Michael P. Clements.  Evaluating Econometric Forecasts of Economic and Financial Variables , 2005 .

[137]  Chris Chatfield,et al.  Confessions of a pragmatic statistician , 2002 .

[138]  E. Lorenz,et al.  The predictability of a flow which possesses many scales of motion , 1969 .

[139]  F. Atger,et al.  The Skill of Ensemble Prediction Systems , 1999 .

[140]  A. H. Murphy,et al.  What Is a Good Forecast? An Essay on the Nature of Goodness in Weather Forecasting , 1993 .

[141]  G. Strbac,et al.  Trading Wind Generation in Short-Term Energy Markets , 2002, IEEE Power Engineering Review.

[142]  G. Carpinelli,et al.  2002 Conference on Probabilistic Methods Applied to Power Systems , 2004 .

[143]  A. H. Murphy,et al.  A General Framework for Forecast Verification , 1987 .

[144]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[145]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[146]  J. Holton.  An introduction to dynamic meteorology , 2004 .

[147]  Eugenia Kalnay,et al.  Three years of operational prediction of forecast skill at NMC , 1995 .

[148]  Henrik Madsen,et al.  Wind power Ensemble forecasting , 2004 .

[149]  R. Baillie,et al.  Prediction in dynamic models with time-dependent conditional variances , 1992 .

[150]  M. Veall,et al.  Bootstrap prediction intervals for single period regression forecasts , 2002 .

[151]  Georges Kariniotakis,et al.  On-line adaptation of confidence intervals based on weather stability for wind power forecasting , 2004 .

[152]  Ulrich Focken,et al.  Short-term prediction of the aggregated power output of wind farms—a statistical analysis of the reduction of the prediction error by spatial smoothing effects , 2002 .

[153]  G. Strbac,et al.  Value of combining energy storage and wind in short-term energy and balancing markets , 2003 .

[154]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[155]  W. H. Williams,et al.  A Simple Method for the Construction of Empirical Confidence Limits for Economic Forecasts , 1971 .

[156]  Peter Hall,et al.  Improving coverage accuracy of nonparametric prediction intervals , 2001 .

[157]  Pierre Pinson,et al.  Standardizing the Performance Evaluation of Short-Term Wind Power Prediction Models , 2005 .

[158]  D.W. Bunn,et al.  Forecasting loads and prices in competitive power markets , 2000, Proceedings of the IEEE.

[159]  J.A.P. Lopes,et al.  On the optimization of the daily operation of a wind-hydro power plant , 2004, IEEE Transactions on Power Systems.

[160]  Detlev Heinemann,et al.  ACCURACY OF SHORT TERM WIND POWER PREDICTIONS DEPENDING ON METEOROLOGICAL CONDITIONS , 2022 .

[161]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[162]  Georges Kariniotakis,et al.  Wind power forecasting using fuzzy neural networks enhanced with on-line prediction risk assessment , 2003, 2003 IEEE Bologna Power Tech Conference Proceedings,.

[163]  Nalini Ravishanker,et al.  Multiple prediction intervals for time series: Comparison of simultaneous and marginal intervals , 1991 .

[164]  James M. Murphy,et al.  The impact of ensemble forecasts on predictability , 1988 .

[165]  T. Hamill.  Interpretation of Rank Histograms for Verifying Ensemble Forecasts , 2001 .

[166]  Detlev Heinemann,et al.  PREVIENTO REGIONAL WIND POWER PREDICTION WITH RISK CONTROL , 2002 .

[167]  Henrik Lund,et al.  Management of surplus electricity-production from a fluctuating renewable-energy source , 2003 .

[168]  E. Kalnay,et al.  Ensemble Forecasting at NCEP and the Breeding Method , 1997 .

[169]  Stephen J. Lord,et al.  Maturity of Operational Numerical Weather Prediction: Medium Range , 1998 .

[170]  Y. M. Saint-Drenan.  Wind power predictions analysis. Part. 1: TenneT imbalance price system. Development of a model for TenneT imbalance price , 2002 .

[171]  R. Buizza,et al.  Neural Network Load Forecasting with Weather Ensemble Predictions , 2002, IEEE Power Engineering Review.

[172]  Henrik Madsen,et al.  Properties of quantile and interval forecasts of wind generation and their evaluation. , 2006 .

[173]  P. S. Dokopoulos,et al.  Wind speed and power forecasting based on spatial correlation models , 1999 .

[174]  Georges Kariniotakis,et al.  Quantification of capacity credit and reserve requirements from the large scale integration of wind energy in the french power system , 2004 .

[175]  Klaus Skytte,et al.  The regulating power market on the Nordic power exchange Nord Pool: an econometric analysis , 1999 .

[176]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[177]  J.B. Theocharis,et al.  A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation , 2004, IEEE Transactions on Energy Conversion.

[178]  Richard Kleeman,et al.  Skill assessment for ENSO using ensemble prediction , 1998 .

[179]  Matthias Lange,et al.  Analysis of the uncertainty of wind power predictions , 2003 .