Estimating the wake losses in large wind farms: A machine learning approach

Estimating the wake losses in a wind farm is critical in the short term forecast of wind power, following the Numerical Weather Prediction (NWP) approach. Understanding the intensity of the wakes and the nature of its propagation within the wind farm still remains a challenge to scientist, engineers and utility operators. In this paper, five different machine learning methods are used to estimate the power deficit experienced by wind turbines due to the wake losses. Production data from the Horns Rev offshore wind farm, Denmark, have been used for the study. The methods used are linear regression, linear regression with feature engineering, nonlinear regression, Artificial Neural Networks (ANN) and Support Vector Regression (SVR). Power developed by individual turbines located at different positions within the farm were computed based on the above methods and compared with the actual power measurements. With the respective Variance Normalized Root Mean Square Error (VNRMSE) of 0.21 and 0.22, models based on ANN and SVR could estimate the wind farm wake effects at an acceptable accuracy level. The study shows that suitable machine learning methods can effectively be used in estimating the power deficits due to wake effects experienced in large wind farms.

[1]  Gunner Chr. Larsen,et al.  Comparison of Wake Models with Data for Offshore Windfarms , 2001 .

[2]  Jiang Chuanwen,et al.  A review on the economic dispatch and risk management considering wind power in the power market , 2009 .

[3]  Leo E. Jensen,et al.  Quantifying the Impact of Wind Turbine Wakes on Power Output at Offshore Wind Farms , 2010 .

[4]  Gregor Giebel,et al.  The State-Of-The-Art in Short-Term Prediction of Wind Power. A Literature Overview , 2003 .

[5]  Rebecca J. Barthelmie,et al.  Analytical modelling of wind speed deficit in large offshore wind farms , 2006 .

[6]  Peng Guo,et al.  A Review of Wind Power Forecasting Models , 2011 .

[7]  Deva P. Seetharam,et al.  An advanced model for the short-term forecast of wind energy , 2011 .

[8]  Gunner Chr. Larsen,et al.  A Simple Wake Calculation Procedure , 1988 .

[9]  E. S. Politis,et al.  Flow and wakes in large wind farms in complex terrain and offshore , 2008 .

[10]  祐子 植田,et al.  Global Wind Energy Outlook 2012 概説 , 2013 .

[11]  Erik Ela,et al.  Economic Evaluation of Short- Term Wind Power Forecasts in ERCOT: Preliminary Results , 2012 .

[12]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[13]  Aoife Foley,et al.  Current methods and advances in forecasting of wind power generation , 2012 .

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

[15]  R. Barthelmie,et al.  The economic benefit of short-term forecasting for wind energy in the UK electricity market , 2008 .

[16]  A. Kusiak,et al.  Short-Term Prediction of Wind Farm Power: A Data Mining Approach , 2009, IEEE Transactions on Energy Conversion.

[17]  E Pelikán,et al.  Wind power forecasting by an empirical model using NWP outputs , 2010, 2010 9th International Conference on Environment and Electrical Engineering.

[18]  N. Jensen.  A note on wind generator interaction , 1983 .