Islanding detection in a distributed generation integrated power system using phase space technique and probabilistic neural network

Aziah Khamis, Hussain Shareef, Azah Mohamed, Erdal Bizkevelci

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

The high penetration level of distributed generation (DG) provides numerous potential environmental benefits, such as high reliability, efficiency, and low carbon emissions. However, the effective detection of islanding and rapid DG disconnection is essential to avoid safety problems and equipment damage caused by the island mode operations of DGs. The common islanding protection technology is based on passive techniques that do not perturb the system but have large non-detection zones. This study attempts to develop a simple and effective passive islanding detection method with reference to a probabilistic neural network-based classifier, as well as utilizes the features extracted from three phase voltages seen at the DG terminal. This approach enables initial features to be obtained using the phase-space technique. This technique analyzes the time series in a higher dimensional space, revealing several hidden features of the original signal. Intensive simulations were conducted using the DigSilent Power Factory® software. Results show that the proposed islanding detection method using probabilistic neural network and phase-space technique is robust and capable of sensing the difference between the islanding condition and other system disturbances.

Original languageEnglish
Pages (from-to)587-599
Number of pages13
JournalNeurocomputing
Volume148
DOIs
Publication statusPublished - 19 Jan 2015

Fingerprint

Distributed power generation
Equipment Safety
Neural networks
Islands
Carbon
Software
Technology
Industrial plants
Time series
Classifiers
Electric potential

Keywords

  • Artificial neural network
  • Distributed generation
  • Islanding detection
  • Non-detection zone
  • Phase space
  • Wavelet transform

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Cognitive Neuroscience

Cite this

Islanding detection in a distributed generation integrated power system using phase space technique and probabilistic neural network. / Khamis, Aziah; Shareef, Hussain; Mohamed, Azah; Bizkevelci, Erdal.

In: Neurocomputing, Vol. 148, 19.01.2015, p. 587-599.

Research output: Contribution to journalArticle

Khamis, Aziah ; Shareef, Hussain ; Mohamed, Azah ; Bizkevelci, Erdal. / Islanding detection in a distributed generation integrated power system using phase space technique and probabilistic neural network. In: Neurocomputing. 2015 ; Vol. 148. pp. 587-599.
@article{0a003f155d0a4e3e9ef530ca72b281f8,
title = "Islanding detection in a distributed generation integrated power system using phase space technique and probabilistic neural network",
abstract = "The high penetration level of distributed generation (DG) provides numerous potential environmental benefits, such as high reliability, efficiency, and low carbon emissions. However, the effective detection of islanding and rapid DG disconnection is essential to avoid safety problems and equipment damage caused by the island mode operations of DGs. The common islanding protection technology is based on passive techniques that do not perturb the system but have large non-detection zones. This study attempts to develop a simple and effective passive islanding detection method with reference to a probabilistic neural network-based classifier, as well as utilizes the features extracted from three phase voltages seen at the DG terminal. This approach enables initial features to be obtained using the phase-space technique. This technique analyzes the time series in a higher dimensional space, revealing several hidden features of the original signal. Intensive simulations were conducted using the DigSilent Power Factory{\circledR} software. Results show that the proposed islanding detection method using probabilistic neural network and phase-space technique is robust and capable of sensing the difference between the islanding condition and other system disturbances.",
keywords = "Artificial neural network, Distributed generation, Islanding detection, Non-detection zone, Phase space, Wavelet transform",
author = "Aziah Khamis and Hussain Shareef and Azah Mohamed and Erdal Bizkevelci",
year = "2015",
month = "1",
day = "19",
doi = "10.1016/j.neucom.2014.07.004",
language = "English",
volume = "148",
pages = "587--599",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - Islanding detection in a distributed generation integrated power system using phase space technique and probabilistic neural network

AU - Khamis, Aziah

AU - Shareef, Hussain

AU - Mohamed, Azah

AU - Bizkevelci, Erdal

PY - 2015/1/19

Y1 - 2015/1/19

N2 - The high penetration level of distributed generation (DG) provides numerous potential environmental benefits, such as high reliability, efficiency, and low carbon emissions. However, the effective detection of islanding and rapid DG disconnection is essential to avoid safety problems and equipment damage caused by the island mode operations of DGs. The common islanding protection technology is based on passive techniques that do not perturb the system but have large non-detection zones. This study attempts to develop a simple and effective passive islanding detection method with reference to a probabilistic neural network-based classifier, as well as utilizes the features extracted from three phase voltages seen at the DG terminal. This approach enables initial features to be obtained using the phase-space technique. This technique analyzes the time series in a higher dimensional space, revealing several hidden features of the original signal. Intensive simulations were conducted using the DigSilent Power Factory® software. Results show that the proposed islanding detection method using probabilistic neural network and phase-space technique is robust and capable of sensing the difference between the islanding condition and other system disturbances.

AB - The high penetration level of distributed generation (DG) provides numerous potential environmental benefits, such as high reliability, efficiency, and low carbon emissions. However, the effective detection of islanding and rapid DG disconnection is essential to avoid safety problems and equipment damage caused by the island mode operations of DGs. The common islanding protection technology is based on passive techniques that do not perturb the system but have large non-detection zones. This study attempts to develop a simple and effective passive islanding detection method with reference to a probabilistic neural network-based classifier, as well as utilizes the features extracted from three phase voltages seen at the DG terminal. This approach enables initial features to be obtained using the phase-space technique. This technique analyzes the time series in a higher dimensional space, revealing several hidden features of the original signal. Intensive simulations were conducted using the DigSilent Power Factory® software. Results show that the proposed islanding detection method using probabilistic neural network and phase-space technique is robust and capable of sensing the difference between the islanding condition and other system disturbances.

KW - Artificial neural network

KW - Distributed generation

KW - Islanding detection

KW - Non-detection zone

KW - Phase space

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=84908069419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908069419&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2014.07.004

DO - 10.1016/j.neucom.2014.07.004

M3 - Article

AN - SCOPUS:84908069419

VL - 148

SP - 587

EP - 599

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -