Comparison of advanced non‐parametric models for wind turbine power curves. Issue 9 (10th April 2019)

• Record Type: Journal Article
• Authors: Pandit, Ravi Kumar; Infield, David; Kolios, Athanasios
• Is Part Of: IET renewable power generation. Volume 13:Issue 9(2019)
• Page Start: 1503
• Page End: 1510
• Publication Date: 2019-04-10
• Subjects: fault diagnosis -- statistical analysis -- support vector machines -- curve fitting -- blades -- wind turbines -- Gaussian processes -- SCADA systems; nonparametric models -- wind turbine power curves -- nonparametric methods -- smooth curves -- continuous curves -- nonparametric techniques -- power curve modelling -- power curve fitting performance -- Gaussian process -- random forest -- support vector machine -- robust fault detection -- supervisory control -- data acquisition; Renewable energy sources -- Periodicals; 333.79405
• DOI: 10.1049/iet-rpg.2018.5728
• Languages: English
• ISSNs: 1752-1416

Abstract

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.