The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method

Tingyan Guo; J. V. Milanovic

doi:10.1109/ISGTEurope.2013.6695256

The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

This paper investigates the practical issues associated with on-line prediction of transient stability using decision tree (DT) method. The issues of quality and availability of the measurement signals provided by wide area measurement system (WAMS) are discussed and their effects on the accuracy of performance of the DT are evaluated. The surrogate split method included in the classification and regression tree (CART) algorithm is used to handle the unavailability of measurement signals, and noise present in the on-line data is modeled as white Gaussian noise (WGN) with various signal-to-noise ratio (SNR). Case studies are carried out in the 16 machine, 68 bus power system. The results quantify the reduction of the performance of the DT method. © 2013 IEEE.

Original language	English
Title of host publication	2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013\|IEEE/PES Innovative Smart Grid Technol. Europe, ISGT Europe
Publisher	IEEE
ISBN (Print)	9781479929849
DOIs	https://doi.org/10.1109/ISGTEurope.2013.6695256
Publication status	Published - 2013
Event	2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013 - Lyngby Duration: 1 Jul 2013 → …

Conference

Conference	2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013
City	Lyngby
Period	1/07/13 → …

Keywords

Decision tree
missing values
noise
phasor measurement units
power system transient stability

Access to Document

10.1109/ISGTEurope.2013.6695256

Cite this

Guo, T., & Milanovic, J. V. (2013). The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method. In 2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013|IEEE/PES Innovative Smart Grid Technol. Europe, ISGT Europe IEEE. https://doi.org/10.1109/ISGTEurope.2013.6695256

@inproceedings{955afd9fcaea457cac0735541f94b84b,

title = "The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method",

abstract = "This paper investigates the practical issues associated with on-line prediction of transient stability using decision tree (DT) method. The issues of quality and availability of the measurement signals provided by wide area measurement system (WAMS) are discussed and their effects on the accuracy of performance of the DT are evaluated. The surrogate split method included in the classification and regression tree (CART) algorithm is used to handle the unavailability of measurement signals, and noise present in the on-line data is modeled as white Gaussian noise (WGN) with various signal-to-noise ratio (SNR). Case studies are carried out in the 16 machine, 68 bus power system. The results quantify the reduction of the performance of the DT method. {\textcopyright} 2013 IEEE.",

keywords = "Decision tree, missing values, noise, phasor measurement units, power system transient stability",

author = "Tingyan Guo and Milanovic, {J. V.}",

year = "2013",

doi = "10.1109/ISGTEurope.2013.6695256",

language = "English",

isbn = "9781479929849",

booktitle = "2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013|IEEE/PES Innovative Smart Grid Technol. Europe, ISGT Europe",

publisher = "IEEE",

address = "United States",

note = "2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013 ; Conference date: 01-07-2013",

}

Guo, T & Milanovic, JV 2013, The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method. in 2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013|IEEE/PES Innovative Smart Grid Technol. Europe, ISGT Europe. IEEE, 2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013, Lyngby, 1/07/13. https://doi.org/10.1109/ISGTEurope.2013.6695256

The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method. / Guo, Tingyan; Milanovic, J. V.
2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013|IEEE/PES Innovative Smart Grid Technol. Europe, ISGT Europe. IEEE, 2013.

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method

AU - Guo, Tingyan

AU - Milanovic, J. V.

PY - 2013

Y1 - 2013

N2 - This paper investigates the practical issues associated with on-line prediction of transient stability using decision tree (DT) method. The issues of quality and availability of the measurement signals provided by wide area measurement system (WAMS) are discussed and their effects on the accuracy of performance of the DT are evaluated. The surrogate split method included in the classification and regression tree (CART) algorithm is used to handle the unavailability of measurement signals, and noise present in the on-line data is modeled as white Gaussian noise (WGN) with various signal-to-noise ratio (SNR). Case studies are carried out in the 16 machine, 68 bus power system. The results quantify the reduction of the performance of the DT method. © 2013 IEEE.

AB - This paper investigates the practical issues associated with on-line prediction of transient stability using decision tree (DT) method. The issues of quality and availability of the measurement signals provided by wide area measurement system (WAMS) are discussed and their effects on the accuracy of performance of the DT are evaluated. The surrogate split method included in the classification and regression tree (CART) algorithm is used to handle the unavailability of measurement signals, and noise present in the on-line data is modeled as white Gaussian noise (WGN) with various signal-to-noise ratio (SNR). Case studies are carried out in the 16 machine, 68 bus power system. The results quantify the reduction of the performance of the DT method. © 2013 IEEE.

KW - Decision tree

KW - missing values

KW - noise

KW - phasor measurement units

KW - power system transient stability

U2 - 10.1109/ISGTEurope.2013.6695256

DO - 10.1109/ISGTEurope.2013.6695256

M3 - Conference contribution

SN - 9781479929849

BT - 2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013|IEEE/PES Innovative Smart Grid Technol. Europe, ISGT Europe

PB - IEEE

T2 - 2013 4th IEEE/PES Innovative Smart Grid Technologies Europe, ISGT Europe 2013

Y2 - 1 July 2013

ER -

The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this