Abstract
To continuously assess the performance of a wind turbine (WT), accurate power curve modelling is essential. Various statistical methods have been used to fit power curves to performance measurements; these are broadly classified into parametric and non-parametric methods. In this study, three advanced non-parametric approaches, namely: Gaussian Process (GP); Random Forest (RF); and Support Vector Machine (SVM) are assessed for WT power curve modelling. The modelled power curves are constructed using historical WT supervisory control and data acquisition, data obtained from operational three bladed pitch regulated WTs. The modelled power curve fitting performance is then compared using suitable performance, error metrics to identify the most accurate approach. It is found that a power curve based on a GP has the highest fitting accuracy, whereas the SVM approach gives poorer but acceptable results, over a restricted wind speed range. Power curves based on a GP or SVM provide smooth and continuous curves, whereas power curves based on the RF technique are neither smooth nor continuous. This study highlights the strengths and weaknesses of the proposed non-parametric techniques to construct a robust fault detection algorithm for WTs based on power curves.
Highlights
Unexpected failures of wind turbine (WT) components, in particular, the rotor, gearbox, and generator, make operation and maintenance (O&M) more expensive and can add significantly to the overall Cost Of Energy (COE)
The advanced nonparametric models (GP, Support vector machine (SVM), and Random Forest (RF)) for estimating WT power curves based on Supervisory control and data acquisition (SCADA) datasets obtained from operational WTs are presented in this paper
Gaussian Process (GP) and SVM are kernel methods while RF is a regression tree method inspired by Classification and Regression Trees (CARTs) principle
Summary
Unexpected failures of wind turbine (WT) components, in particular, the rotor, gearbox, and generator, make operation and maintenance (O&M) more expensive and can add significantly to the overall Cost Of Energy (COE). Support vector machine (SVM) is another nonparametric method that has been introduced for wind turbine power curve modeling [27,28] Both methods suffer from a number of practical issues such the cubic inversion issue associated with larger data sets. It is essential to investigate the performance of different nonparametric techniques for power curve modeling to evaluate which technique is more accurate for a given dataset Advanced nonparametric models such as the GP, SVM and RF are gaining popularity because of their low computational cost and high accuracy. The paper presents the implementation of three advanced nonparametric algorithms (GP, SVM, and RF) for modeling of wind turbine power curves, and their accuracy has been compared using error performance metrics (RMSE, R2, MAE). Performance Error metrics, residuals analysis and uncertainty analysis, are used to compare the performance of the models and based on this comparison, best approach for Wind Turbine power curve modeling is being suggested
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
