Decision tree assisted controlled islanding for preventing cascading events

Ruisheng Diao, Vijay Vittal, Kai Sun, Sharma Kolluri, S. Mandal, F. Galvan

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

36 Citations (Scopus)

Abstract

At stressed operating conditions, critical contingencies can initiate loss of synchronism and trigger cascading events. Controlled islanding is the last line of defense to stabilize the whole system. This paper presents a decision tree assisted scheme to determine the timing of controlled islanding in real time by using phasor measurements. In addition, a slow coherency based approach is used to determine where to island. This scheme is tested on the operational model of the Entergy system and a severe N-2 outage case is used to demonstrate the phenomenon of cascading events due to protective relay actions. The results show that training one decision tree only for a specified critical contingency that can potentially cause cascading events can yields high prediction accuracy. Being aware of loss of synchronism in real time, operators can implement controlled islanding at carefully designed transmission interfaces and rapidly stabilize each island. Thus a significant amount of load is still served compared to uncontrolled system islanding.

Original languageEnglish (US)
Title of host publication2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009
DOIs
StatePublished - 2009
Event2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009 - Seattle, WA, United States
Duration: Mar 15 2009Mar 18 2009

Other

Other2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009
CountryUnited States
CitySeattle, WA
Period3/15/093/18/09

Fingerprint

Decision trees
Synchronization
Phasor measurement units
Relay protection
Outages

Keywords

  • Controlled islanding
  • Decision trees
  • Load shedding
  • Phasor measurement units
  • Protective relays
  • System islanding
  • Transient stability prediction

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Diao, R., Vittal, V., Sun, K., Kolluri, S., Mandal, S., & Galvan, F. (2009). Decision tree assisted controlled islanding for preventing cascading events. In 2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009 [4839985] https://doi.org/10.1109/PSCE.2009.4839985

Decision tree assisted controlled islanding for preventing cascading events. / Diao, Ruisheng; Vittal, Vijay; Sun, Kai; Kolluri, Sharma; Mandal, S.; Galvan, F.

2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009. 2009. 4839985.

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

Diao, R, Vittal, V, Sun, K, Kolluri, S, Mandal, S & Galvan, F 2009, Decision tree assisted controlled islanding for preventing cascading events. in 2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009., 4839985, 2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009, Seattle, WA, United States, 3/15/09. https://doi.org/10.1109/PSCE.2009.4839985
Diao R, Vittal V, Sun K, Kolluri S, Mandal S, Galvan F. Decision tree assisted controlled islanding for preventing cascading events. In 2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009. 2009. 4839985 https://doi.org/10.1109/PSCE.2009.4839985
Diao, Ruisheng ; Vittal, Vijay ; Sun, Kai ; Kolluri, Sharma ; Mandal, S. ; Galvan, F. / Decision tree assisted controlled islanding for preventing cascading events. 2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009. 2009.
@inproceedings{b32d7c7458b64ae6a33c4c56ebf59d49,
title = "Decision tree assisted controlled islanding for preventing cascading events",
abstract = "At stressed operating conditions, critical contingencies can initiate loss of synchronism and trigger cascading events. Controlled islanding is the last line of defense to stabilize the whole system. This paper presents a decision tree assisted scheme to determine the timing of controlled islanding in real time by using phasor measurements. In addition, a slow coherency based approach is used to determine where to island. This scheme is tested on the operational model of the Entergy system and a severe N-2 outage case is used to demonstrate the phenomenon of cascading events due to protective relay actions. The results show that training one decision tree only for a specified critical contingency that can potentially cause cascading events can yields high prediction accuracy. Being aware of loss of synchronism in real time, operators can implement controlled islanding at carefully designed transmission interfaces and rapidly stabilize each island. Thus a significant amount of load is still served compared to uncontrolled system islanding.",
keywords = "Controlled islanding, Decision trees, Load shedding, Phasor measurement units, Protective relays, System islanding, Transient stability prediction",
author = "Ruisheng Diao and Vijay Vittal and Kai Sun and Sharma Kolluri and S. Mandal and F. Galvan",
year = "2009",
doi = "10.1109/PSCE.2009.4839985",
language = "English (US)",
isbn = "9781424438112",
booktitle = "2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009",

}

TY - GEN

T1 - Decision tree assisted controlled islanding for preventing cascading events

AU - Diao, Ruisheng

AU - Vittal, Vijay

AU - Sun, Kai

AU - Kolluri, Sharma

AU - Mandal, S.

AU - Galvan, F.

PY - 2009

Y1 - 2009

N2 - At stressed operating conditions, critical contingencies can initiate loss of synchronism and trigger cascading events. Controlled islanding is the last line of defense to stabilize the whole system. This paper presents a decision tree assisted scheme to determine the timing of controlled islanding in real time by using phasor measurements. In addition, a slow coherency based approach is used to determine where to island. This scheme is tested on the operational model of the Entergy system and a severe N-2 outage case is used to demonstrate the phenomenon of cascading events due to protective relay actions. The results show that training one decision tree only for a specified critical contingency that can potentially cause cascading events can yields high prediction accuracy. Being aware of loss of synchronism in real time, operators can implement controlled islanding at carefully designed transmission interfaces and rapidly stabilize each island. Thus a significant amount of load is still served compared to uncontrolled system islanding.

AB - At stressed operating conditions, critical contingencies can initiate loss of synchronism and trigger cascading events. Controlled islanding is the last line of defense to stabilize the whole system. This paper presents a decision tree assisted scheme to determine the timing of controlled islanding in real time by using phasor measurements. In addition, a slow coherency based approach is used to determine where to island. This scheme is tested on the operational model of the Entergy system and a severe N-2 outage case is used to demonstrate the phenomenon of cascading events due to protective relay actions. The results show that training one decision tree only for a specified critical contingency that can potentially cause cascading events can yields high prediction accuracy. Being aware of loss of synchronism in real time, operators can implement controlled islanding at carefully designed transmission interfaces and rapidly stabilize each island. Thus a significant amount of load is still served compared to uncontrolled system islanding.

KW - Controlled islanding

KW - Decision trees

KW - Load shedding

KW - Phasor measurement units

KW - Protective relays

KW - System islanding

KW - Transient stability prediction

UR - http://www.scopus.com/inward/record.url?scp=70349190373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349190373&partnerID=8YFLogxK

U2 - 10.1109/PSCE.2009.4839985

DO - 10.1109/PSCE.2009.4839985

M3 - Conference contribution

AN - SCOPUS:70349190373

SN - 9781424438112

BT - 2009 IEEE/PES Power Systems Conference and Exposition, PSCE 2009

ER -