Abstract

Controlled islanding refers to the controlled separation of an interconnected power system into electrically isolated regions. The objective of this paper is to develop adaptive controlled islanding as a component of an emergency power system control strategy. There are two primary aspects of controlled islanding: 1) where to island and 2) when to island? Assisted by a decision tree (DT) approach, this paper seeks to address the "when to island" aspect. A decision tree based tool is proposed to recognize conditions existing in the system that warrant controlled islanding. A 29-generator, 179-bus system is employed to demonstrate the tool. Simulation data are used to train DTs, and the online performance of DTs is then evaluated as part of a controlled islanding strategy.

Original languageEnglish (US)
Pages (from-to)1790-1797
Number of pages8
JournalIEEE Transactions on Power Systems
Volume21
Issue number4
DOIs
StatePublished - Nov 2006

Fingerprint

Decision trees
Electric power system interconnection
Control systems

Keywords

  • Controlled islanding
  • Decision tree
  • Machine learning
  • Power system stability
  • R-Rdot relay
  • Self healing
  • Special protection systems

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Decision tree assisted controlled islanding. / Senroy, Nilanjan; Heydt, Gerald T.; Vittal, Vijay.

In: IEEE Transactions on Power Systems, Vol. 21, No. 4, 11.2006, p. 1790-1797.

Research output: Contribution to journalArticle

@article{017d25df329a482781f2415de4435035,
title = "Decision tree assisted controlled islanding",
abstract = "Controlled islanding refers to the controlled separation of an interconnected power system into electrically isolated regions. The objective of this paper is to develop adaptive controlled islanding as a component of an emergency power system control strategy. There are two primary aspects of controlled islanding: 1) where to island and 2) when to island? Assisted by a decision tree (DT) approach, this paper seeks to address the {"}when to island{"} aspect. A decision tree based tool is proposed to recognize conditions existing in the system that warrant controlled islanding. A 29-generator, 179-bus system is employed to demonstrate the tool. Simulation data are used to train DTs, and the online performance of DTs is then evaluated as part of a controlled islanding strategy.",
keywords = "Controlled islanding, Decision tree, Machine learning, Power system stability, R-Rdot relay, Self healing, Special protection systems",
author = "Nilanjan Senroy and Heydt, {Gerald T.} and Vijay Vittal",
year = "2006",
month = "11",
doi = "10.1109/TPWRS.2006.882470",
language = "English (US)",
volume = "21",
pages = "1790--1797",
journal = "IEEE Transactions on Power Systems",
issn = "0885-8950",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Decision tree assisted controlled islanding

AU - Senroy, Nilanjan

AU - Heydt, Gerald T.

AU - Vittal, Vijay

PY - 2006/11

Y1 - 2006/11

N2 - Controlled islanding refers to the controlled separation of an interconnected power system into electrically isolated regions. The objective of this paper is to develop adaptive controlled islanding as a component of an emergency power system control strategy. There are two primary aspects of controlled islanding: 1) where to island and 2) when to island? Assisted by a decision tree (DT) approach, this paper seeks to address the "when to island" aspect. A decision tree based tool is proposed to recognize conditions existing in the system that warrant controlled islanding. A 29-generator, 179-bus system is employed to demonstrate the tool. Simulation data are used to train DTs, and the online performance of DTs is then evaluated as part of a controlled islanding strategy.

AB - Controlled islanding refers to the controlled separation of an interconnected power system into electrically isolated regions. The objective of this paper is to develop adaptive controlled islanding as a component of an emergency power system control strategy. There are two primary aspects of controlled islanding: 1) where to island and 2) when to island? Assisted by a decision tree (DT) approach, this paper seeks to address the "when to island" aspect. A decision tree based tool is proposed to recognize conditions existing in the system that warrant controlled islanding. A 29-generator, 179-bus system is employed to demonstrate the tool. Simulation data are used to train DTs, and the online performance of DTs is then evaluated as part of a controlled islanding strategy.

KW - Controlled islanding

KW - Decision tree

KW - Machine learning

KW - Power system stability

KW - R-Rdot relay

KW - Self healing

KW - Special protection systems

UR - http://www.scopus.com/inward/record.url?scp=33847630861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847630861&partnerID=8YFLogxK

U2 - 10.1109/TPWRS.2006.882470

DO - 10.1109/TPWRS.2006.882470

M3 - Article

AN - SCOPUS:33847630861

VL - 21

SP - 1790

EP - 1797

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

SN - 0885-8950

IS - 4

ER -