Performance Assessment of Wind Turbines: Data-Derived Quantitative Metrics

被引：76

作者：

He, Yusen ^{[1
]}

Kusiak, Andrew ^{[1
]}

机构：

[1] Univ Iowa, Mech & Ind Engn Dept, Iowa City, IA 52242 USA

来源：

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY | 2018年 / 9卷 / 01期

关键词：

Extreme learning machine; linear ensemble; performance metrics; parametric Copula models; tail dependence analysis; wind turbine performance evaluation; EXTREME LEARNING-MACHINE; POWER-GENERATION; ENERGY; REGRESSION; MODELS;

D O I：

10.1109/TSTE.2017.2715061

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Deteriorating performance of wind turbines results in power loses. A two-phase approach for performance evaluation of wind turbines is presented at past and future time intervals. Historical wind turbine data is utilized to determine the past performance, while performance at future time horizons calls for power prediction. In phase I of the proposed approach, wind power is predicted by an ensemble of extreme learning machines using parameters such as wind speed, air temperature, and the rotor speed. In phase II, the predicted power is used to construct Copula models. It has been demonstrated that the parameters of the Copula models serve as usable metrics for expressing performance of wind turbines. The Frank Copula model performs best among the five parametric models tested.

引用

页码：65 / 73

页数：9

共 42 条

[21]

Lendasse A, 2013, LECT NOTES COMPUT SC, V7902, P17, DOI 10.1007/978-3-642-38679-4_2

[22] Classification of mental tasks from EEG signals using extreme learning machine [J].

Liang, NY ;

Saratchandran, P ;

Huang, GB ;

Sundararajan, N .

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2006, 16 (01) :29-38

[23] Unit sizing and cost analysis of stand-alone hybrid wind/PV/fuel cell power generation systems [J].

Nelson, D. B. ;

Nehrir, M. H. ;

Wang, C. .

RENEWABLE ENERGY, 2006, 31 (10) :1641-1656

[24] Very short-term wind forecasting for Tasmanian power generation [J].

Potter, CW ;

Negnevitsky, M .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2006, 21 (02) :965-972

[25] How do crude oil prices co-move? A copula approach [J].

Reboredo, Juan C. .

ENERGY ECONOMICS, 2011, 33 (05) :948-955

[26] Theoretical and empirical analysis of ReliefF and RReliefF [J].

Robnik-Sikonja, M ;

Kononenko, I .

MACHINE LEARNING, 2003, 53 (1-2) :23-69

[27] Application of Latent Nestling Method using Coloured Petri Nets for the Fault Diagnosis in the Wind Turbine Subsets [J].

Rodriguez, L. ;

Garcia, E. ;

Morant, F. ;

Correcher, A. ;

Quiles, E. .

2008 IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION, PROCEEDINGS, 2008, :767-773

[28] RETRACTED: Application of extreme learning machine for estimation of wind speed distribution (Retracted Article) [J].

Shamshirband, Shahaboddin ;

Mohammadi, Kasra ;

Tong, Chong Wen ;

Petkovic, Dalibor ;

Porcu, Emilio ;

Mostafaeipour, Ali ;

Ch, Sudheer ;

Sedaghat, Ahmad .

CLIMATE DYNAMICS, 2016, 46 (5-6) :1893-1907

[29]

Singh R, 2007, INT J INTELLIGENT TE, V2, P256

[30] Reliability of wind turbine subassemblies [J].

Spinato, F. ;

Tavner, P. J. ;

van Bussel, G. J. W. ;

Koutoulakos, E. .

IET RENEWABLE POWER GENERATION, 2009, 3 (04) :387-401

← 1 2 3 4 5 →