Comparison of advanced non-parametric models for wind turbine power curves

被引:37
作者
Pandit, Ravi Kumar [1 ]
Infield, David [1 ]
Kolios, Athanasios [2 ]
机构
[1] Univ Strathclyde, Dept Elect & Elect Engn, 16 Richmond St, Glasgow G1 1XQ, Lanark, Scotland
[2] Univ Strathclyde, Dept Naval Architecture Ocean & Marine Engn, 16 Richmond St, Glasgow G1 1XQ, Lanark, Scotland
基金
欧盟地平线“2020”;
关键词
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; FAULT-DIAGNOSIS; RANDOM FORESTS; DECOMPOSITION; PREDICTION;
D O I
10.1049/iet-rpg.2018.5728
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
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.
引用
收藏
页码:1503 / 1510
页数:8
相关论文
共 50 条
[21]   Estimation of wind turbine output power using soft computing models [J].
Tumse, Sergen ;
Ilhan, Akin ;
Bilgili, Mehmet ;
Sahin, Besir .
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2022, 44 (02) :3757-3786
[22]   Performance Comparison of Metaheuristic Optimization-Based Parametric Methods in Wind Turbine Power Curve Modeling [J].
Yesilbudak, Mehmet ;
Ozcan, Ahmet .
IEEE ACCESS, 2024, 12 :99372-99381
[23]   Comparison of non-parametric methods in genomic evaluation of discrete traits [J].
Targhi, Mohammad Vahid Abolhassani ;
Jafarabadi, Ghobad Asgari ;
Aminafshar, Mehdi ;
Kashan, Nasser Emam Jomeh .
GENE REPORTS, 2019, 15
[24]   Parametric and Non-parametric Models To Estimate Households' Willingness To Pay For Improved Management of Watershed [J].
Carandang, Myrna G. ;
Calderon, Margaret M. ;
Camacho, Leni D. ;
Dizon, Josefina T. .
JOURNAL OF ENVIRONMENTAL SCIENCE AND MANAGEMENT, 2008, 11 (02) :68-78
[25]   Probabilistic and deterministic wind speed forecasting based on non-parametric approaches and wind characteristics information [J].
Heng, Jiani ;
Hong, Yongmiao ;
Hu, Jianming ;
Wang, Shouyang .
APPLIED ENERGY, 2022, 306
[26]   Comparison of parametric and non-parametric estimations of the annual date of positive water temperature onset [J].
Daigle, Anik ;
Ouarda, Taha B. M. J. ;
Bilodeau, Laurent .
JOURNAL OF HYDROLOGY, 2010, 390 (1-2) :75-84
[27]   Intelligent Models for the Power Curves of Small Wind Turbines [J].
Veena, R. ;
Femin, V ;
Mathew, S. ;
Petra, I ;
Hazra, J. .
PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON COGENERATION, SMALL POWER PLANTS AND DISTRICT ENERGY (ICUE 2016), 2016,
[28]   Multivariate Data-Driven Models for Wind Turbine Power Curves including Sub-Component Temperatures [J].
Astolfi, Davide ;
Pandit, Ravi ;
Lombardi, Andrea ;
Terzi, Ludovico .
ENERGIES, 2023, 16 (01)
[29]   Wind Turbine Power Curves Based on the Weibull Cumulative Distribution Function [J].
Bokde, Neeraj ;
Feijoo, Andres ;
Villanueva, Daniel .
APPLIED SCIENCES-BASEL, 2018, 8 (10)
[30]   A SURVEY OF SOFTWARE RELIABILITY GROWTH MODELS USING NON-PARAMETRIC METHODS [J].
Saley, M. K. ;
Sreedharan, Sasikumaran .
2014 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH (IEEE ICCIC), 2014, :563-567