Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals

Ravi Kumar Pandit; David Infield

doi:10.1109/ICCEP.2017.8004774

Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals

Ravi Kumar Pandit, David Infield

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

12 Citations (Scopus)

59 Downloads (Pure)

Abstract

High operation and maintenance (O&M) costs may affect the profitability and growth of wind turbine industries in long term, especially where offshore wind farms are concerned. With the increase in age of wind turbines and the expansion of offshore wind, the operation and maintenance (O&M) cost is expected to grow significantly which reinforces the drive towards condition based maintenance. Wind turbine power curves play a central role in the assessment of turbine operational health. Gaussian process theory is finding increasing application in this current emerging research area. This paper investigates the potential of Gaussian process models to improve the representation of wind turbine power curves and in particular the importance of confidence intervals as determined by such modeling.

Original language	English
Title of host publication	2017 6th International Conference on Clean Electrical Power (ICCEP)
Place of Publication	Piscataway, N.J.
Publisher	IEEE
Pages	744-749
Number of pages	6
ISBN (Print)	978-1-5090-4683-6
DOIs	https://doi.org/10.1109/ICCEP.2017.8004774
Publication status	Published - 18 Aug 2017
Event	6th International Conference on CLEAN ELECTRICAL POWER Renewable Energy Resources Impact - Santa Margherita Ligure, Liguria, Italy Duration: 27 Jun 2017 → 29 Jun 2017 http://www.iccep.net/

Conference

Conference	6th International Conference on CLEAN ELECTRICAL POWER Renewable Energy Resources Impact
Country/Territory	Italy
City	Liguria
Period	27/06/17 → 29/06/17
Internet address	http://www.iccep.net/

Keywords

wind turbine
gaussian process models
condition monitoring
SCADA data
power curve

Access to Document

10.1109/ICCEP.2017.8004774

Pandit-Infield-ICCEP-2017-Using-Gaussian-process-theory-for-wind-turbine-powerAccepted author manuscript, 786 KB

Cite this

@inproceedings{bb2e1c60edef4a6dba18db41a5f6b7c2,

title = "Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals",

abstract = "High operation and maintenance (O&M) costs may affect the profitability and growth of wind turbine industries in long term, especially where offshore wind farms are concerned. With the increase in age of wind turbines and the expansion of offshore wind, the operation and maintenance (O&M) cost is expected to grow significantly which reinforces the drive towards condition based maintenance. Wind turbine power curves play a central role in the assessment of turbine operational health. Gaussian process theory is finding increasing application in this current emerging research area. This paper investigates the potential of Gaussian process models to improve the representation of wind turbine power curves and in particular the importance of confidence intervals as determined by such modeling.",

keywords = "wind turbine, gaussian process models, condition monitoring, SCADA data, power curve",

author = "Pandit, {Ravi Kumar} and David Infield",

note = "{\textcopyright} 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 6th International Conference on CLEAN ELECTRICAL POWER Renewable Energy Resources Impact ; Conference date: 27-06-2017 Through 29-06-2017",

year = "2017",

month = aug,

day = "18",

doi = "10.1109/ICCEP.2017.8004774",

language = "English",

isbn = "978-1-5090-4683-6",

pages = "744--749",

booktitle = "2017 6th International Conference on Clean Electrical Power (ICCEP)",

publisher = "IEEE",

url = "http://www.iccep.net/",

}

Pandit, RK & Infield, D 2017, Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals. in 2017 6th International Conference on Clean Electrical Power (ICCEP). IEEE, Piscataway, N.J., pp. 744-749, 6th International Conference on CLEAN ELECTRICAL POWER Renewable Energy Resources Impact, Liguria, Italy, 27/06/17. https://doi.org/10.1109/ICCEP.2017.8004774

TY - GEN

T1 - Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals

AU - Pandit, Ravi Kumar

AU - Infield, David

N1 - © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2017/8/18

Y1 - 2017/8/18

N2 - High operation and maintenance (O&M) costs may affect the profitability and growth of wind turbine industries in long term, especially where offshore wind farms are concerned. With the increase in age of wind turbines and the expansion of offshore wind, the operation and maintenance (O&M) cost is expected to grow significantly which reinforces the drive towards condition based maintenance. Wind turbine power curves play a central role in the assessment of turbine operational health. Gaussian process theory is finding increasing application in this current emerging research area. This paper investigates the potential of Gaussian process models to improve the representation of wind turbine power curves and in particular the importance of confidence intervals as determined by such modeling.

AB - High operation and maintenance (O&M) costs may affect the profitability and growth of wind turbine industries in long term, especially where offshore wind farms are concerned. With the increase in age of wind turbines and the expansion of offshore wind, the operation and maintenance (O&M) cost is expected to grow significantly which reinforces the drive towards condition based maintenance. Wind turbine power curves play a central role in the assessment of turbine operational health. Gaussian process theory is finding increasing application in this current emerging research area. This paper investigates the potential of Gaussian process models to improve the representation of wind turbine power curves and in particular the importance of confidence intervals as determined by such modeling.

KW - wind turbine

KW - gaussian process models

KW - condition monitoring

KW - SCADA data

KW - power curve

UR - https://ieeexplore.ieee.org/abstract/document/8004774/

U2 - 10.1109/ICCEP.2017.8004774

DO - 10.1109/ICCEP.2017.8004774

M3 - Conference contribution book

SN - 978-1-5090-4683-6

SP - 744

EP - 749

BT - 2017 6th International Conference on Clean Electrical Power (ICCEP)

PB - IEEE

CY - Piscataway, N.J.

T2 - 6th International Conference on CLEAN ELECTRICAL POWER Renewable Energy Resources Impact

Y2 - 27 June 2017 through 29 June 2017

ER -

Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

AWESOME (H2020 ETN)

Comparative analysis of Gaussian Process power curve models based on different stationary covariance functions for the purpose of improving model accuracy

Comparative analysis of binning and support vector regression for wind turbine rotor speed based power curve use in condition monitoring

Comparative assessments of binned and support vector regression-based blade pitch curve of a wind turbine for the purpose of condition monitoring

Marie Curie Early stage reseacher

Cite this

Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

AWESOME (H2020 ETN)

Research output

Comparative analysis of Gaussian Process power curve models based on different stationary covariance functions for the purpose of improving model accuracy

Comparative analysis of binning and support vector regression for wind turbine rotor speed based power curve use in condition monitoring

Comparative assessments of binned and support vector regression-based blade pitch curve of a wind turbine for the purpose of condition monitoring

Prizes

Marie Curie Early stage reseacher

Cite this