Fast online identification of power system dynamic behaviour

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

Fast online identification of power system dynamic behaviour

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

Electronic And Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

12 Downloads (Pure)

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.

Original language	English
Number of pages	5
Publication status	Published - 20 Jul 2017
Event	2017 IEEE Power and Energy Society General Meeting, PESGM 2017 - Chicago, United States Duration: 16 Jul 2017 → 20 Jul 2017

Conference

Conference	2017 IEEE Power and Energy Society General Meeting, PESGM 2017
Country/Territory	United States
City	Chicago
Period	16/07/17 → 20/07/17

Keywords

decision trees
dynamic security assessment
online transient stability

Access to Document

Papadopoulos-etal-PESGM2017-Fast-online-identification-of-power-system-dynamic-behaviourAccepted author manuscript, 814 KB

https://www.research.manchester.ac.uk/portal/en/publications/fast-online-identification-of-power-system-dynamic-behaviour(3a10c0b0-a382-44d7-abaa-dae300031198).html

Cite this

Papadopoulos, P. N., Bhui, P., Milanovic, J. V., & Senroy, N. (2017). Fast online identification of power system dynamic behaviour. Paper presented at 2017 IEEE Power and Energy Society General Meeting, PESGM 2017, Chicago, United States. https://www.research.manchester.ac.uk/portal/en/publications/fast-online-identification-of-power-system-dynamic-behaviour(3a10c0b0-a382-44d7-abaa-dae300031198).html

@conference{782d2f7f5b024331b81d852a3a47a4b0,

title = "Fast online identification of power system dynamic behaviour",

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 Pratyasa Bhui and Milanovic, {Jovica V.} and Nilanjan Senroy",

year = "2017",

month = jul,

day = "20",

language = "English",

note = "2017 IEEE Power and Energy Society General Meeting, PESGM 2017 ; Conference date: 16-07-2017 Through 20-07-2017",

}

Papadopoulos, PN, Bhui, P, Milanovic, JV & Senroy, N 2017, 'Fast online identification of power system dynamic behaviour', Paper presented at 2017 IEEE Power and Energy Society General Meeting, PESGM 2017, Chicago, United States, 16/07/17 - 20/07/17. <https://www.research.manchester.ac.uk/portal/en/publications/fast-online-identification-of-power-system-dynamic-behaviour(3a10c0b0-a382-44d7-abaa-dae300031198).html>

TY - CONF

T1 - Fast online identification of power system dynamic behaviour

AU - Papadopoulos, Panagiotis N.

AU - Bhui, Pratyasa

AU - Milanovic, Jovica V.

AU - Senroy, Nilanjan

PY - 2017/7/20

Y1 - 2017/7/20

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

M3 - Paper

T2 - 2017 IEEE Power and Energy Society General Meeting, PESGM 2017

Y2 - 16 July 2017 through 20 July 2017

ER -

Fast online identification of power system dynamic behaviour

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this