Performance comparison of artificial intelligence techniques for non-intrusive electrical load monitoring

Khairuddin Khalid, Azah Mohamed, Ramizi Mohamed, Hussain Shareef

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval.

Original languageEnglish
Pages (from-to)143-152
Number of pages10
JournalBulletin of Electrical Engineering and Informatics
Volume7
Issue number2
DOIs
Publication statusPublished - 1 Jun 2018

Fingerprint

Smart meters
artificial intelligence
Performance Comparison
Artificial intelligence
Artificial Intelligence
Monitoring
Learning systems
Signal analysis
Reactive power
Personal computers
Extreme Learning Machine
Support vector machines
Feature extraction
Loads (forces)
machine learning
Energy utilization
Electricity
Mathematical transformations
classifying
Neural networks

Keywords

  • Artificial neural network (ANN)
  • Extreme learning machine
  • Non-intrusive load monitoring
  • Support vector machine

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Control and Systems Engineering
  • Information Systems
  • Instrumentation
  • Hardware and Architecture
  • Computer Networks and Communications
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

Performance comparison of artificial intelligence techniques for non-intrusive electrical load monitoring. / Khalid, Khairuddin; Mohamed, Azah; Mohamed, Ramizi; Shareef, Hussain.

In: Bulletin of Electrical Engineering and Informatics, Vol. 7, No. 2, 01.06.2018, p. 143-152.

Research output: Contribution to journalArticle

@article{c8e828fcc2874c309660169be8738b4d,
title = "Performance comparison of artificial intelligence techniques for non-intrusive electrical load monitoring",
abstract = "The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100{\%} accuracy for data sampled at 1 minute time interval.",
keywords = "Artificial neural network (ANN), Extreme learning machine, Non-intrusive load monitoring, Support vector machine",
author = "Khairuddin Khalid and Azah Mohamed and Ramizi Mohamed and Hussain Shareef",
year = "2018",
month = "6",
day = "1",
doi = "10.11591/eei.v7i2.1190",
language = "English",
volume = "7",
pages = "143--152",
journal = "Bulletin of Electrical Engineering and Informatics",
issn = "2089-3191",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "2",

}

TY - JOUR

T1 - Performance comparison of artificial intelligence techniques for non-intrusive electrical load monitoring

AU - Khalid, Khairuddin

AU - Mohamed, Azah

AU - Mohamed, Ramizi

AU - Shareef, Hussain

PY - 2018/6/1

Y1 - 2018/6/1

N2 - The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval.

AB - The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval.

KW - Artificial neural network (ANN)

KW - Extreme learning machine

KW - Non-intrusive load monitoring

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85049906195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049906195&partnerID=8YFLogxK

U2 - 10.11591/eei.v7i2.1190

DO - 10.11591/eei.v7i2.1190

M3 - Article

AN - SCOPUS:85049906195

VL - 7

SP - 143

EP - 152

JO - Bulletin of Electrical Engineering and Informatics

JF - Bulletin of Electrical Engineering and Informatics

SN - 2089-3191

IS - 2

ER -