Comparative study in determining features extraction for islanding detection using data mining technique: Correlation and coefficient analysis

Aziah Khamis, Yan Xu, Azah Mohamed

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A comprehensive comparison study on the data mining based approaches for detecting islanding events in a power distribution system with inverter-based distributed generations is presented. The important features for each phase in the island detection scheme are investigated in detail. These features are extracted from the time-varying measurements of voltage, frequency and total harmonic distortion (THD) of current and voltage at the point of common coupling. Numerical studies were conducted on the IEEE 34-bus system considering various scenarios of islanding and non-islanding conditions. The features obtained are then used to train several data mining techniques such as decision tree, support vector machine, neural network, bagging and random forest (RF). The simulation results showed that the important feature parameters can be evaluated based on the correlation between the extracted features. From the results, the four important features that give accurate islanding detection are the fundamental voltage THD, fundamental current THD, rate of change of voltage magnitude and voltage deviation. Comparison studies demonstrated the effectiveness of the RF method in achieving high accuracy for islanding detection.

Original languageEnglish
Pages (from-to)1112-1124
Number of pages13
JournalInternational Journal of Electrical and Computer Engineering
Volume7
Issue number3
DOIs
Publication statusPublished - 1 Jun 2017

Fingerprint

Data mining
Feature extraction
Harmonic distortion
Electric potential
Distributed power generation
Decision trees
Support vector machines
Neural networks

Keywords

  • Data-mining
  • Distributed Generation
  • Islanding Detection
  • Random Forest

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

@article{d68d1b738001473880e1559558413d79,
title = "Comparative study in determining features extraction for islanding detection using data mining technique: Correlation and coefficient analysis",
abstract = "A comprehensive comparison study on the data mining based approaches for detecting islanding events in a power distribution system with inverter-based distributed generations is presented. The important features for each phase in the island detection scheme are investigated in detail. These features are extracted from the time-varying measurements of voltage, frequency and total harmonic distortion (THD) of current and voltage at the point of common coupling. Numerical studies were conducted on the IEEE 34-bus system considering various scenarios of islanding and non-islanding conditions. The features obtained are then used to train several data mining techniques such as decision tree, support vector machine, neural network, bagging and random forest (RF). The simulation results showed that the important feature parameters can be evaluated based on the correlation between the extracted features. From the results, the four important features that give accurate islanding detection are the fundamental voltage THD, fundamental current THD, rate of change of voltage magnitude and voltage deviation. Comparison studies demonstrated the effectiveness of the RF method in achieving high accuracy for islanding detection.",
keywords = "Data-mining, Distributed Generation, Islanding Detection, Random Forest",
author = "Aziah Khamis and Yan Xu and Azah Mohamed",
year = "2017",
month = "6",
day = "1",
doi = "10.11591/ijece.v7i3.pp1112-1124",
language = "English",
volume = "7",
pages = "1112--1124",
journal = "International Journal of Electrical and Computer Engineering",
issn = "2088-8708",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "3",

}

TY - JOUR

T1 - Comparative study in determining features extraction for islanding detection using data mining technique

T2 - Correlation and coefficient analysis

AU - Khamis, Aziah

AU - Xu, Yan

AU - Mohamed, Azah

PY - 2017/6/1

Y1 - 2017/6/1

N2 - A comprehensive comparison study on the data mining based approaches for detecting islanding events in a power distribution system with inverter-based distributed generations is presented. The important features for each phase in the island detection scheme are investigated in detail. These features are extracted from the time-varying measurements of voltage, frequency and total harmonic distortion (THD) of current and voltage at the point of common coupling. Numerical studies were conducted on the IEEE 34-bus system considering various scenarios of islanding and non-islanding conditions. The features obtained are then used to train several data mining techniques such as decision tree, support vector machine, neural network, bagging and random forest (RF). The simulation results showed that the important feature parameters can be evaluated based on the correlation between the extracted features. From the results, the four important features that give accurate islanding detection are the fundamental voltage THD, fundamental current THD, rate of change of voltage magnitude and voltage deviation. Comparison studies demonstrated the effectiveness of the RF method in achieving high accuracy for islanding detection.

AB - A comprehensive comparison study on the data mining based approaches for detecting islanding events in a power distribution system with inverter-based distributed generations is presented. The important features for each phase in the island detection scheme are investigated in detail. These features are extracted from the time-varying measurements of voltage, frequency and total harmonic distortion (THD) of current and voltage at the point of common coupling. Numerical studies were conducted on the IEEE 34-bus system considering various scenarios of islanding and non-islanding conditions. The features obtained are then used to train several data mining techniques such as decision tree, support vector machine, neural network, bagging and random forest (RF). The simulation results showed that the important feature parameters can be evaluated based on the correlation between the extracted features. From the results, the four important features that give accurate islanding detection are the fundamental voltage THD, fundamental current THD, rate of change of voltage magnitude and voltage deviation. Comparison studies demonstrated the effectiveness of the RF method in achieving high accuracy for islanding detection.

KW - Data-mining

KW - Distributed Generation

KW - Islanding Detection

KW - Random Forest

UR - http://www.scopus.com/inward/record.url?scp=85021122764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021122764&partnerID=8YFLogxK

U2 - 10.11591/ijece.v7i3.pp1112-1124

DO - 10.11591/ijece.v7i3.pp1112-1124

M3 - Article

AN - SCOPUS:85021122764

VL - 7

SP - 1112

EP - 1124

JO - International Journal of Electrical and Computer Engineering

JF - International Journal of Electrical and Computer Engineering

SN - 2088-8708

IS - 3

ER -