Modeling of a Robust Confidence Band for the Power Curve of a Wind Turbine
AbstractHaving an accurate model of the power curve of a wind turbine allows us to better monitor its operation and planning of storage capacity. Since wind speed and direction is of a highly stochastic nature, the forecasting of the power generated by the wind turbine is of the same nature as well. In this paper, a method for obtaining a robust confidence band containing the power curve of a wind turbine under test conditions is presented. Here, the confidence band is bound by two curves which are estimated using parametric statistical inference techniques. However, the observations that are used for carrying out the statistical analysis are obtained by using the binning method, and in each bin, the outliers are eliminated by using a censorship process based on robust statistical techniques. Then, the observations that are not outliers are divided into observation sets. Finally, both the power curve of the wind turbine and the two curves that define the robust confidence band are estimated using each of the previously mentioned observation sets. View Full-Text
Share & Cite This Article
Hernandez, W.; Méndez, A.; Maldonado-Correa, J.L.; Balleteros, F. Modeling of a Robust Confidence Band for the Power Curve of a Wind Turbine. Sensors 2016, 16, 2080.
Hernandez W, Méndez A, Maldonado-Correa JL, Balleteros F. Modeling of a Robust Confidence Band for the Power Curve of a Wind Turbine. Sensors. 2016; 16(12):2080.Chicago/Turabian Style
Hernandez, Wilmar; Méndez, Alfredo; Maldonado-Correa, Jorge L.; Balleteros, Francisco. 2016. "Modeling of a Robust Confidence Band for the Power Curve of a Wind Turbine." Sensors 16, no. 12: 2080.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.