On the use of robust regression methods in wind speed assessment

Wind climate analysis and modelling is of most importance during site selection for offshore wind farm development. In this regard, reliable long-term wind data are required. Buoy measurements are considered as a reference source in relevant applications including evaluation and calibration of wind data obtained from less reliable sources, combined assessment, blending and homogenization of multi-source wind data, etc. Most of these applications are based on regression techniques elaborated by using the principle of ordinary least squares (OLS). However, wind data usually contain several outliers, which may question the validity of the regression analysis, if not properly considered. This study is focused on the implementation of the most important robust regression methods, which can identify and reveal outliers, and retain at the same time their efficiency. Long-term reference wind data series obtained from buoys at six locations in the Mediterranean Sea are used to calibrate hindcast (model) wind data by applying robust methods and OLS. The obtained results are compared according to several statistical measures. The effects of the calibration methods are also assessed with respect to the available wind power potential. The results clearly suggest that least trimmed squares and L1-estimator perform in all respects better than OLS.

[1]  P. J. Huber.  The behavior of maximum likelihood estimates under nonstandard conditions , 1967 .

[2]  P. Rousseeuw,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .

[3]  James F. Manwell,et al.  Comparison of the performance of four measure–correlate–predict algorithms , 2005 .

[4]  J. O. Rawlings,et al.  Applied Regression Analysis: A Research Tool , 1988 .

[5]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .

[6]  N. M. Nielsen,et al.  Offshore Wind Turbine Wakes Measured by Sodar , 2003 .

[7]  Pin T. Ng,et al.  A Frisch-Newton Algorithm for Sparse Quantile Regression , 2005 .

[8]  J. Gower,et al.  Intercalibration of wave and wind data from TOPEX/POSEIDON and moored buoys off the west coast of Canada , 1996 .

[9]  G. Kallos,et al.  The Weather Forecasting System for Poseidon - an Overview , 2002 .

[10]  J. A. Carta,et al.  A review of measure-correlate-predict (MCP) methods used to estimate long-term wind characteristics at a target site , 2013 .

[11]  James F. Manwell,et al.  Uncertainty Analysis in MCP-Based Wind Resource Assessment and Energy Production Estimation , 2008 .

[12]  P. Rousseeuw,et al.  Generalized S-Estimators , 1994 .

[13]  Takvor H. Soukissian,et al.  About applying linear structural method on ocean data: Adjustment of satellite wave data , 2007 .

[14]  Vic Barnett,et al.  Outliers in Statistical Data , 1980 .

[15]  F. Hampel.  The Influence Curve and Its Role in Robust Estimation , 1974 .

[16]  N. Draper,et al.  Applied Regression Analysis , 1967 .

[17]  David B. Gilhousen,et al.  A Field Evaluation of NDBC Moored Buoy Winds , 1987 .

[18]  S. Chatterjee,et al.  Influential Observations, High Leverage Points, and Outliers in Linear Regression , 1986 .

[19]  S. Sheather,et al.  Robust Estimation and Testing , 1990 .

[20]  José Jesús Guerrero,et al.  Robust filtering for the characterization of wind turbines: Improving its operation and maintenance , 2009 .

[21]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[22]  Stephane Heritier,et al.  Robust Methods in Biostatistics , 2009 .

[23]  Thomas P. Ryan,et al.  Modern Regression Methods , 1996 .

[24]  V. Yohai.  HIGH BREAKDOWN-POINT AND HIGH EFFICIENCY ROBUST ESTIMATES FOR REGRESSION , 1987 .

[25]  Werner A. Stahel,et al.  Sharpening Wald-type inference in robust regression for small samples , 2011, Comput. Stat. Data Anal..

[26]  H. Jørgensen,et al.  Wind lidar evaluation at the Danish wind test site in Høvsøre , 2006 .

[27]  Werner A. Stahel,et al.  Robust Statistics: The Approach Based on Influence Functions , 1987 .

[28]  Takvor H. Soukissian,et al.  Effects of different wind data sources in offshore wind power assessment , 2015 .

[29]  P. J. Huber.  Robust Estimation of a Location Parameter , 1964 .

[30]  Peter Rousseeuw,et al.  Econometric Applications of High-Breakdown Robust Regression Techniques , 2017, 1709.00181.

[31]  Louis A. Jaeckel.  Estimating Regression Coefficients by Minimizing the Dispersion of the Residuals , 1972 .

[32]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[33]  Takvor H. Soukissian,et al.  Poseidon: A marine environmental monitoring, forecasting and information system for the Greek seas , 2000 .

[34]  F. Hampel.  A General Qualitative Definition of Robustness , 1971 .

[35]  Charu C. Aggarwal,et al.  Outlier Analysis , 2013, Springer New York.

[36]  J. Tukey.  The Future of Data Analysis , 1962 .

[37]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[38]  P. J. Huber.  Robust Regression: Asymptotics, Conjectures and Monte Carlo , 1973 .

[39]  R. Wilcox.  Introduction to Robust Estimation and Hypothesis Testing , 1997 .