Search

This paper analyses the influence of the variation of meteorological and operational parameters on estimation of the power output of a dispatchable wind farm (WF). The active power set-points (APSPs), established to regulate the wind farm power output (WFPO), are one of the analysed parameters. The WF considered as case study is integrated in the Gorona del Viento wind-hydro power plant (El Hierro-Canary Islands-Spain), which supplies the primary energy demand of the island. Statistical inference between the errors generated by different WFPO estimation models, each fed with different input features, is performed. These models are based on supervised machine learning (ML) regression algorithms, namely support vector regression, random forest, and a combination of the strengths of these two base learning algorithms constructed using stacked regression ensemble techniques. From the results obtained, the following conclusions are drawn: a) There is a marked difference between the errors obtained with the model that only considers wind speed and direction and that which additionally incorporates the APSP parameter, showing the importance of considering this particular parameter; b) the model which incorporates air density and turbulence intensity in addition to the APSP improves the values of all the metrics, independently of the ML technique employed. • The active power set-point (APSP) parameter is very important in WFPO estimation. • Air density, turbulence intensity and APSP parameters improve WFPO estimation. • Eight models are compared for wind farm power output (WFPO) estimation. • Three machine learning techniques implemented in the models are analysed. • Non-parametric statistical inference is used to compare the models. [ABSTRACT FROM AUTHOR]