Use of Bayesian networks classifiers for long-term mean wind turbine energy output estimation at a potential wind energy conversion site

Abstract Due to the interannual variability of wind speed a feasibility analysis for the installation of a Wind Energy Conversion System at a particular site requires estimation of the long-term mean wind turbine energy output. A method is proposed in this paper which, based on probabilistic Bayesian networks (BNs), enables estimation of the long-term mean wind speed histogram for a site where few measurements of the wind resource are available. For this purpose, the proposed method allows the use of multiple reference stations with a long history of wind speed and wind direction measurements. That is to say, the model that is proposed in this paper is able to involve and make use of regional information about the wind resource. With the estimated long-term wind speed histogram and the power curve of a wind turbine it is possible to use the method of bins to determine the long-term mean energy output for that wind turbine. The intelligent system employed, the knowledgebase of which is a joint probability function of all the model variables, uses efficient calculation techniques for conditional probabilities to perform the reasoning. This enables automatic model learning and inference to be performed efficiently based on the available evidence. The proposed model is applied in this paper to wind speeds and wind directions recorded at four weather stations located in the Canary Islands (Spain). Ten years of mean hourly wind speed and direction data are available for these stations. One of the conclusions reached is that the BN with three reference stations gave fewer errors between the real and estimated long-term mean wind turbine energy output than when using two measure–correlate–predict algorithms which were evaluated and which use a linear regression between the candidate station and one reference station.

[1]  Ramón García-Rojo.  Algorithm for the Estimation of the Long-Term Wind Climate at a Meteorological Mast Using a Joint Probabilistic Approach , 2004 .

[2]  J. A. Carta,et al.  A review of wind speed probability distributions used in wind energy analysis: Case studies in the Canary Islands , 2009 .

[3]  Simon J. Watson,et al.  A new matrix method of predicting long-term wind roses with MCP , 1997 .

[4]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[5]  V. Barros,et al.  On the Evaluation of Wind Power from Short Wind Records , 1983 .

[6]  José A. Carta,et al.  Self-Sufficient Energy Supply for Isolated Communities: Wind-Diesel Systems in the Canary Islands , 2001 .

[7]  C. Pritchard,et al.  European Wind Energy Conference , 2002 .

[8]  E. Sreevalsan,et al.  Wind Farm Site Assessment Using Measure—Correlate-Predict (MCP) Analysis , 2007 .

[9]  Florence.  European community wind energy conference , 1993 .

[10]  José A. Carta,et al.  Influence of the level of fit of a density probability function to wind-speed data on the WECS mean power output estimation , 2008 .

[11]  Richard E. Neapolitan,et al.  Learning Bayesian networks , 2007, KDD '07.

[12]  Helmut E. Landsberg,et al.  Methods in Climatology , 1945 .

[13]  Ahmet Öztopal,et al.  Artificial neural network approach to spatial estimation of wind velocity data , 2006 .

[14]  P. Putnam.  Power from the wind , 1948 .

[15]  Doug Fisher,et al.  Learning from Data: Artificial Intelligence and Statistics V , 1996 .

[16]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[17]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

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

[19]  T. Akai.  Applied numerical methods for engineers , 1994 .

[20]  Vladimir Cherkassky,et al.  Learning from data , 1998 .

[21]  J. P. Deane,et al.  Wind resource assessment of an area using short term data correlated to a long term data set , 2004 .

[22]  J. A. Carta,et al.  A continuous bivariate model for wind power density and wind turbine energy output estimations , 2007 .

[23]  C. G. Justus,et al.  Interannual and Month-to-Month Variations of Wind Speed , 1978 .

[24]  J. A. Carta,et al.  A joint probability density function of wind speed and direction for wind energy analysis , 2008 .

[25]  W. T. Pennell,et al.  The siting handbook for large wind energy systems , 1981 .

[26]  José Manuel Gutiérrez,et al.  IMPLEMENTATION OF DATA MINING TECHNIQUES FOR METEOROLOGICAL APPLICATIONS , 2003 .

[27]  A. R. Jha,et al.  Wind Turbine Technology , 2010 .

[28]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[29]  J. Mcgowan,et al.  Wind Energy Explained , 2002 .

[30]  Palmer Cosslett Putnam,et al.  Putnam's Power from the wind , 1974 .

[31]  Ian Witten,et al.  Data Mining , 2000 .

[32]  Enrique F. Castillo,et al.  Expert Systems and Probabilistic Network Models , 1996, Monographs in Computer Science.

[33]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.