A feature-based diagnosis framework for power plant model validation

Meng Wu, Le Xie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There has been increasing recognition of the importance of utilizing phasor measurement units (PMUs) for power plant model validation (PPMV). In North America, the PMU-based PPMV is typically performed manually by utilities and independent system operators (ISOs) for diagnosing and calibrating power plant model problems. In order to guarantee the accuracy of the calibration results, engineers need to provide manual judgment to the mismatched PPMV cases, so that the type of the modeling problem (such as wrong machine parameters, missing governor models, etc.) can be determined before the model is sent for a detailed calibration. This manual judgment process has become the major bottleneck for automating the PMU-based PPMV. To overcome this difficulty, this paper proposes a feature-based diagnosis framework to determining the types of the power plant model problems. It mimics the human engineering judgment process via a supervised learning approach. Instead of applying purely curve fitting or sensitivity analysis, this approach uses the engineering experience extracted from the labeled historical PPMV cases, establish the critical feature space, and then perform artificial learning to determine the type of a power plant model problem. The proposed framework could serve as a screening tool for the PPMV engineering judgment process, which could potentially help automate the entire PMU-based PPMV applications.

Original languageEnglish (US)
Title of host publication20th Power Systems Computation Conference, PSCC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781910963104
DOIs
StatePublished - Aug 20 2018
Event20th Power Systems Computation Conference, PSCC 2018 - Dublin, Ireland
Duration: Jun 11 2018Jun 15 2018

Other

Other20th Power Systems Computation Conference, PSCC 2018
CountryIreland
CityDublin
Period6/11/186/15/18

Fingerprint

Power plants
Phasor measurement units
Calibration
Governors
Supervised learning
Curve fitting
Human engineering
Sensitivity analysis
Screening
Engineers

Keywords

  • Machine learning
  • Phasor measurement unit
  • Power plant model validation
  • Problem diagnosis

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality

Cite this

Wu, M., & Xie, L. (2018). A feature-based diagnosis framework for power plant model validation. In 20th Power Systems Computation Conference, PSCC 2018 [8442668] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/PSCC.2018.8442668

A feature-based diagnosis framework for power plant model validation. / Wu, Meng; Xie, Le.

20th Power Systems Computation Conference, PSCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8442668.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, M & Xie, L 2018, A feature-based diagnosis framework for power plant model validation. in 20th Power Systems Computation Conference, PSCC 2018., 8442668, Institute of Electrical and Electronics Engineers Inc., 20th Power Systems Computation Conference, PSCC 2018, Dublin, Ireland, 6/11/18. https://doi.org/10.23919/PSCC.2018.8442668
Wu M, Xie L. A feature-based diagnosis framework for power plant model validation. In 20th Power Systems Computation Conference, PSCC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8442668 https://doi.org/10.23919/PSCC.2018.8442668
Wu, Meng ; Xie, Le. / A feature-based diagnosis framework for power plant model validation. 20th Power Systems Computation Conference, PSCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{8a83e39f5d2c457b92ac577e0dfbe316,
title = "A feature-based diagnosis framework for power plant model validation",
abstract = "There has been increasing recognition of the importance of utilizing phasor measurement units (PMUs) for power plant model validation (PPMV). In North America, the PMU-based PPMV is typically performed manually by utilities and independent system operators (ISOs) for diagnosing and calibrating power plant model problems. In order to guarantee the accuracy of the calibration results, engineers need to provide manual judgment to the mismatched PPMV cases, so that the type of the modeling problem (such as wrong machine parameters, missing governor models, etc.) can be determined before the model is sent for a detailed calibration. This manual judgment process has become the major bottleneck for automating the PMU-based PPMV. To overcome this difficulty, this paper proposes a feature-based diagnosis framework to determining the types of the power plant model problems. It mimics the human engineering judgment process via a supervised learning approach. Instead of applying purely curve fitting or sensitivity analysis, this approach uses the engineering experience extracted from the labeled historical PPMV cases, establish the critical feature space, and then perform artificial learning to determine the type of a power plant model problem. The proposed framework could serve as a screening tool for the PPMV engineering judgment process, which could potentially help automate the entire PMU-based PPMV applications.",
keywords = "Machine learning, Phasor measurement unit, Power plant model validation, Problem diagnosis",
author = "Meng Wu and Le Xie",
year = "2018",
month = "8",
day = "20",
doi = "10.23919/PSCC.2018.8442668",
language = "English (US)",
isbn = "9781910963104",
booktitle = "20th Power Systems Computation Conference, PSCC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A feature-based diagnosis framework for power plant model validation

AU - Wu, Meng

AU - Xie, Le

PY - 2018/8/20

Y1 - 2018/8/20

N2 - There has been increasing recognition of the importance of utilizing phasor measurement units (PMUs) for power plant model validation (PPMV). In North America, the PMU-based PPMV is typically performed manually by utilities and independent system operators (ISOs) for diagnosing and calibrating power plant model problems. In order to guarantee the accuracy of the calibration results, engineers need to provide manual judgment to the mismatched PPMV cases, so that the type of the modeling problem (such as wrong machine parameters, missing governor models, etc.) can be determined before the model is sent for a detailed calibration. This manual judgment process has become the major bottleneck for automating the PMU-based PPMV. To overcome this difficulty, this paper proposes a feature-based diagnosis framework to determining the types of the power plant model problems. It mimics the human engineering judgment process via a supervised learning approach. Instead of applying purely curve fitting or sensitivity analysis, this approach uses the engineering experience extracted from the labeled historical PPMV cases, establish the critical feature space, and then perform artificial learning to determine the type of a power plant model problem. The proposed framework could serve as a screening tool for the PPMV engineering judgment process, which could potentially help automate the entire PMU-based PPMV applications.

AB - There has been increasing recognition of the importance of utilizing phasor measurement units (PMUs) for power plant model validation (PPMV). In North America, the PMU-based PPMV is typically performed manually by utilities and independent system operators (ISOs) for diagnosing and calibrating power plant model problems. In order to guarantee the accuracy of the calibration results, engineers need to provide manual judgment to the mismatched PPMV cases, so that the type of the modeling problem (such as wrong machine parameters, missing governor models, etc.) can be determined before the model is sent for a detailed calibration. This manual judgment process has become the major bottleneck for automating the PMU-based PPMV. To overcome this difficulty, this paper proposes a feature-based diagnosis framework to determining the types of the power plant model problems. It mimics the human engineering judgment process via a supervised learning approach. Instead of applying purely curve fitting or sensitivity analysis, this approach uses the engineering experience extracted from the labeled historical PPMV cases, establish the critical feature space, and then perform artificial learning to determine the type of a power plant model problem. The proposed framework could serve as a screening tool for the PPMV engineering judgment process, which could potentially help automate the entire PMU-based PPMV applications.

KW - Machine learning

KW - Phasor measurement unit

KW - Power plant model validation

KW - Problem diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85054039185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054039185&partnerID=8YFLogxK

U2 - 10.23919/PSCC.2018.8442668

DO - 10.23919/PSCC.2018.8442668

M3 - Conference contribution

AN - SCOPUS:85054039185

SN - 9781910963104

BT - 20th Power Systems Computation Conference, PSCC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -