Statistical description of the error on wind power forecasts via a Lévy α-stable distribution

As the share of wind power in the electricity system rises, the limited predictability of wind power generation becomes increasingly critical for operating a reliable electricity system. In most operational & economic models, the wind power forecast error (WPFE) is often assumed to have a Gaussian or so-called -distribution. However, these distributions are not suited to fully describe the skewed and heavy-tailed character of WPFE data. In this paper, the Levy -stable distribution is proposed as an improved description of the WPFE. Based on 6 years of historical wind power data, three forecast scenarios with forecast horizons ranging from 1 to 24 hours are simulated via a persistence approach. The Levy -stable distribution models the WPFE better than the Gaussian or so-called -distribution, especially for short term forecasts. In a case study, an analysis of historical WPFE data showed improvements over the Gaussian and -distribution between 137 and 567% in terms of cumulative squared residuals. The method presented allows to quantify the probability of a certain error, given a certain wind power forecast. This new statistical description of the WPFE can hold important information for short term economic & operational (reliability) studies in the field of wind power.

[1]  H. Madsen,et al.  From probabilistic forecasts to statistical scenarios of short-term wind power production , 2009 .

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

[3]  N. Menemenlis,et al.  Computation of Dynamic Operating Balancing Reserve for Wind Power Integration for the Time-Horizon 1–48 Hours , 2012, IEEE Transactions on Sustainable Energy.

[4]  B. M. Hill,et al.  A Simple General Approach to Inference About the Tail of a Distribution , 1975 .

[5]  William D'haeseleer,et al.  Adaptive mixed-integer programming unit commitment strategy for determining the value of forecasting , 2008 .

[6]  Pierre Pinson,et al.  Estimation of the uncertainty in wind power forecasting , 2006 .

[7]  T. Kozubowski,et al.  Multivariate geometric stable distributions in financial applications , 1999 .

[8]  H. Bludszuweit,et al.  A Probabilistic Method for Energy Storage Sizing Based on Wind Power Forecast Uncertainty , 2011, IEEE Transactions on Power Systems.

[9]  R. G. Laha.  Review: V. M. Zolotarev, One-dimensional stable distributions , 1989 .

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

[11]  Kristin Dietrich,et al.  Stochastic Unit Commitment Considering Uncertain Wind Production: Application to an isolated system , 2009 .

[12]  R. Weron.  Levy-stable distributions revisited: tail index > 2 does not exclude the Levy-stable regime , 2001, cond-mat/0103256.

[13]  R. Adler,et al.  A practical guide to heavy tails: statistical techniques and applications , 1998 .

[14]  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.

[15]  E. Fama.  The Behavior of Stock-Market Prices , 1965 .

[16]  S. Janson.  Stable distributions , 2011, 1112.0220.

[17]  Emilio Gómez-Lázaro,et al.  Wind Power Forecasting Error Distributions : An International Comparison , 2012 .

[18]  Ronnie Belmans,et al.  Assessment of imbalance settlement exemptions for offshore wind power generation in Belgium , 2011 .

[19]  V. Zolotarev.  One-dimensional stable distributions , 1986 .

[20]  Kabir K. Dutta,et al.  A Tale of Tails: An Empirical Analysis of Loss Distribution Models for Estimating Operational Risk Capital , 2006 .

[21]  J. Huston McCulloch,et al.  13 Financial applications of stable distributions , 1996 .

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

[23]  Kuo‐Chin Hsu,et al.  The use of the Levy-stable distribution for geophysical data analysis , 2009 .

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

[25]  A. Llombart,et al.  Statistical Analysis of Wind Power Forecast Error , 2008, IEEE Transactions on Power Systems.

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

[27]  J. Nolan,et al.  Fitting Data and Assessing Goodness � of � t with Stable Distributions , 1999 .

[28]  Bri-Mathias Hodge,et al.  Wind power forecasting error distributions over multiple timescales , 2011, 2011 IEEE Power and Energy Society General Meeting.

[29]  John P. Nolan,et al.  An overview of multivariate stable distributions , 1996 .

[30]  J. L. Nolan.  Stable Distributions. Models for Heavy Tailed Data , 2001 .

[31]  M. Taqqu,et al.  Stable Non-Gaussian Random Processes : Stochastic Models with Infinite Variance , 1995 .

[32]  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 .

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

[34]  Wei-Jen Lee,et al.  An Integration of ANN Wind Power Estimation Into Unit Commitment Considering the Forecasting Uncertainty , 2007, IEEE Transactions on Industry Applications.

[35]  Tomasz J. Kozubowski,et al.  Geometric stable laws: Estimation and applications , 1999 .

[36]  W.L. Kling,et al.  Impacts of Wind Power on Thermal Generation Unit Commitment and Dispatch , 2007, IEEE Transactions on Energy Conversion.

[37]  R. D. Pierce.  Application of the positive alpha-stable distribution , 1997, Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics.

[38]  J. Nolan,et al.  Modeling financial data with stable distributions , 2003 .

[39]  B. Mandelbrot.  The Variation of Certain Speculative Prices , 1963 .

[40]  C. L. Nikias,et al.  Signal processing with alpha-stable distributions and applications , 1995 .

[41]  V. Zolotarev,et al.  Chance and Stability, Stable Distributions and Their Applications , 1999 .

[42]  William D'haeseleer,et al.  The actual effect of wind power on overall electricity generation costs and CO2 emissions , 2009 .

[43]  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.

[44]  F. Bouffard,et al.  Stochastic security for operations planning with significant wind power generation , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[45]  Vladimiro Miranda,et al.  Wind power forecasting : state-of-the-art 2009. , 2009 .

[46]  S. Tewari,et al.  A Statistical Model for Wind Power Forecast Error and its Application to the Estimation of Penalties in Liberalized Markets , 2011, IEEE Transactions on Power Systems.

[47]  Szymon Borak,et al.  Models for Heavy-tailed Asset Returns , 2010 .

[48]  Jian Ma,et al.  Operational Impacts of Wind Generation on California Power Systems , 2009, IEEE Transactions on Power Systems.

[49]  J. Bouchaud,et al.  Theory of financial risks : from statistical physics to risk management , 2000 .

[50]  Henrik Madsen,et al.  Skill forecasting from ensemble predictions of wind power , 2009 .

[51]  N. L. Johnson,et al.  Continuous Univariate Distributions. , 1995 .

[52]  J. McCulloch,et al.  Simple consistent estimators of stable distribution parameters , 1986 .