Fast online identification of power system dynamic behavior

Panagiotis N. Papadopoulos, Jovica V. Milanovic, Pratyasa Bhui, Nilanjan Senroy

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

2 Citations (Scopus)

Abstract

This paper discusses the methodology for fast prediction of power system dynamic behavior. A combination of features that can be obtained from PMU data is proposed, that can improve the prediction time while keeping high accuracy of prediction. Several combinations of features including generator rotor angles, kinetic energy, acceleration and energy margin are used to train and test decision trees for the online identification of unstable generator groups. The predictor importance for trained decision trees is also calculated to highlight in more detail the effect of using different predictors.

LanguageEnglish
Title of host publication2017 IEEE Power and Energy Society General Meeting, PESGM 2017
Place of PublicationPiscataway, N.J.
PublisherIEEE
Pages1-5
Number of pages5
ISBN (Print)978-1-5386-2212-4
DOIs
Publication statusPublished - 1 Feb 2018
Event2017 IEEE Power and Energy Society General Meeting, PESGM 2017 - Chicago, United States
Duration: 16 Jul 201720 Jul 2017

Conference

Conference2017 IEEE Power and Energy Society General Meeting, PESGM 2017
CountryUnited States
CityChicago
Period16/07/1720/07/17

Fingerprint

Dynamical systems
Decision trees
Kinetic energy
Rotors

Keywords

  • decision trees
  • dynamic security assessment
  • online transient stability

Cite this

Papadopoulos, P. N., Milanovic, J. V., Bhui, P., & Senroy, N. (2018). Fast online identification of power system dynamic behavior. In 2017 IEEE Power and Energy Society General Meeting, PESGM 2017 (pp. 1-5). Piscataway, N.J.: IEEE. https://doi.org/10.1109/PESGM.2017.8273882
Papadopoulos, Panagiotis N. ; Milanovic, Jovica V. ; Bhui, Pratyasa ; Senroy, Nilanjan. / Fast online identification of power system dynamic behavior. 2017 IEEE Power and Energy Society General Meeting, PESGM 2017. Piscataway, N.J. : IEEE, 2018. pp. 1-5
@inproceedings{87ba8f24609641388778b22ac2e1d343,
title = "Fast online identification of power system dynamic behavior",
abstract = "This paper discusses the methodology for fast prediction of power system dynamic behavior. A combination of features that can be obtained from PMU data is proposed, that can improve the prediction time while keeping high accuracy of prediction. Several combinations of features including generator rotor angles, kinetic energy, acceleration and energy margin are used to train and test decision trees for the online identification of unstable generator groups. The predictor importance for trained decision trees is also calculated to highlight in more detail the effect of using different predictors.",
keywords = "decision trees, dynamic security assessment, online transient stability",
author = "Papadopoulos, {Panagiotis N.} and Milanovic, {Jovica V.} and Pratyasa Bhui and Nilanjan Senroy",
year = "2018",
month = "2",
day = "1",
doi = "10.1109/PESGM.2017.8273882",
language = "English",
isbn = "978-1-5386-2212-4",
pages = "1--5",
booktitle = "2017 IEEE Power and Energy Society General Meeting, PESGM 2017",
publisher = "IEEE",

}

Papadopoulos, PN, Milanovic, JV, Bhui, P & Senroy, N 2018, Fast online identification of power system dynamic behavior. in 2017 IEEE Power and Energy Society General Meeting, PESGM 2017. IEEE, Piscataway, N.J., pp. 1-5, 2017 IEEE Power and Energy Society General Meeting, PESGM 2017, Chicago, United States, 16/07/17. https://doi.org/10.1109/PESGM.2017.8273882

Fast online identification of power system dynamic behavior. / Papadopoulos, Panagiotis N.; Milanovic, Jovica V.; Bhui, Pratyasa; Senroy, Nilanjan.

2017 IEEE Power and Energy Society General Meeting, PESGM 2017. Piscataway, N.J. : IEEE, 2018. p. 1-5.

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

TY - GEN

T1 - Fast online identification of power system dynamic behavior

AU - Papadopoulos, Panagiotis N.

AU - Milanovic, Jovica V.

AU - Bhui, Pratyasa

AU - Senroy, Nilanjan

PY - 2018/2/1

Y1 - 2018/2/1

N2 - This paper discusses the methodology for fast prediction of power system dynamic behavior. A combination of features that can be obtained from PMU data is proposed, that can improve the prediction time while keeping high accuracy of prediction. Several combinations of features including generator rotor angles, kinetic energy, acceleration and energy margin are used to train and test decision trees for the online identification of unstable generator groups. The predictor importance for trained decision trees is also calculated to highlight in more detail the effect of using different predictors.

AB - This paper discusses the methodology for fast prediction of power system dynamic behavior. A combination of features that can be obtained from PMU data is proposed, that can improve the prediction time while keeping high accuracy of prediction. Several combinations of features including generator rotor angles, kinetic energy, acceleration and energy margin are used to train and test decision trees for the online identification of unstable generator groups. The predictor importance for trained decision trees is also calculated to highlight in more detail the effect of using different predictors.

KW - decision trees

KW - dynamic security assessment

KW - online transient stability

UR - http://www.scopus.com/inward/record.url?scp=85046349156&partnerID=8YFLogxK

U2 - 10.1109/PESGM.2017.8273882

DO - 10.1109/PESGM.2017.8273882

M3 - Conference contribution book

SN - 978-1-5386-2212-4

SP - 1

EP - 5

BT - 2017 IEEE Power and Energy Society General Meeting, PESGM 2017

PB - IEEE

CY - Piscataway, N.J.

ER -

Papadopoulos PN, Milanovic JV, Bhui P, Senroy N. Fast online identification of power system dynamic behavior. In 2017 IEEE Power and Energy Society General Meeting, PESGM 2017. Piscataway, N.J.: IEEE. 2018. p. 1-5 https://doi.org/10.1109/PESGM.2017.8273882