Event-based S-transform approach for nonintrusive load monitoring

Khairuddin Khalid; Azah Mohamed; Hussain Shareef; Maytham Sabeeh

doi:10.15199/48.2016.05.38

Event-based S-transform approach for nonintrusive load monitoring

Khairuddin Khalid
, Azah Mohamed
, Hussain Shareef
, Maytham Sabeeh

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

In this study, a nonintrusive load monitoring system is developed by analyzing the power signal obtained from a single point of power meter installation to detect ON/OFF load activities. A mathematically designed model with backpropagation neural network is utilized in load pattern recognition to decompose the load operation. Leveraging its unique load signature profile, the S-transform approach is employed to extract the features from the aggregate power signal and analyze the detection of load start-up transient from signal processing. To improve the accuracy of load identification for unknown data, the power factor is used as an additive feature with 99.32% load recognition accuracy.

Original language	English
Pages (from-to)	194-198
Number of pages	5
Journal	Przeglad Elektrotechniczny
Volume	92
Issue number	5
DOIs	https://doi.org/10.15199/48.2016.05.38
Publication status	Published - Apr 1 2016
Externally published	Yes

Keywords

Artificial neural network
Feature extraction
Load recognition
S-transform

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.15199/48.2016.05.38

Cite this

@article{84b8431ce0564511b4cba3b832df8ec8,

title = "Event-based S-transform approach for nonintrusive load monitoring",

abstract = "In this study, a nonintrusive load monitoring system is developed by analyzing the power signal obtained from a single point of power meter installation to detect ON/OFF load activities. A mathematically designed model with backpropagation neural network is utilized in load pattern recognition to decompose the load operation. Leveraging its unique load signature profile, the S-transform approach is employed to extract the features from the aggregate power signal and analyze the detection of load start-up transient from signal processing. To improve the accuracy of load identification for unknown data, the power factor is used as an additive feature with 99.32\% load recognition accuracy.",

keywords = "Artificial neural network, Feature extraction, Load recognition, S-transform",

author = "Khairuddin Khalid and Azah Mohamed and Hussain Shareef and Maytham Sabeeh",

year = "2016",

month = apr,

day = "1",

doi = "10.15199/48.2016.05.38",

language = "English",

volume = "92",

pages = "194--198",

journal = "Przeglad Elektrotechniczny",

issn = "0033-2097",

publisher = "Wydawnictwo SIGMA-NOT",

number = "5",

}

TY - JOUR

T1 - Event-based S-transform approach for nonintrusive load monitoring

AU - Khalid, Khairuddin

AU - Mohamed, Azah

AU - Shareef, Hussain

AU - Sabeeh, Maytham

PY - 2016/4/1

Y1 - 2016/4/1

N2 - In this study, a nonintrusive load monitoring system is developed by analyzing the power signal obtained from a single point of power meter installation to detect ON/OFF load activities. A mathematically designed model with backpropagation neural network is utilized in load pattern recognition to decompose the load operation. Leveraging its unique load signature profile, the S-transform approach is employed to extract the features from the aggregate power signal and analyze the detection of load start-up transient from signal processing. To improve the accuracy of load identification for unknown data, the power factor is used as an additive feature with 99.32% load recognition accuracy.

AB - In this study, a nonintrusive load monitoring system is developed by analyzing the power signal obtained from a single point of power meter installation to detect ON/OFF load activities. A mathematically designed model with backpropagation neural network is utilized in load pattern recognition to decompose the load operation. Leveraging its unique load signature profile, the S-transform approach is employed to extract the features from the aggregate power signal and analyze the detection of load start-up transient from signal processing. To improve the accuracy of load identification for unknown data, the power factor is used as an additive feature with 99.32% load recognition accuracy.

KW - Artificial neural network

KW - Feature extraction

KW - Load recognition

KW - S-transform

UR - https://www.scopus.com/pages/publications/84964865470

UR - https://www.scopus.com/pages/publications/84964865470#tab=citedBy

U2 - 10.15199/48.2016.05.38

DO - 10.15199/48.2016.05.38

M3 - Article

AN - SCOPUS:84964865470

SN - 0033-2097

VL - 92

SP - 194

EP - 198

JO - Przeglad Elektrotechniczny

JF - Przeglad Elektrotechniczny

IS - 5

ER -

Event-based S-transform approach for nonintrusive load monitoring

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this