Nonintrusive load monitoring using TT-transform and neural networks

Khairuddin Khalid, Azah Mohamed, Hussain Shareef

Research output: Contribution to journalArticle

Abstract

This paper presents nonintrusive load monitoring (NILM) method using the TT-transform feature extraction technique and multilayer perceptron with back-propagation neural network. The low sampling rate of load data were measured by using a smart meter to provide information on the operation of the loads such as air conditioner, personal computer and lighting. The accuracy of load identification with event based method is dependent on the measured signals and the selected features. To improve the identification of various types of loads, the TT-transform feature extraction technique is applied so as to provide additional features for characterizing the loads. Based on the load data obtained from the smart meter, the different features extracted such as real power, reactive power, power factor, apparent power, impedance, event signal (ΔP) and TT-transform features. These features are used as inputs to MLP-BPNN for identifying the various types of loads. The neural network is validated by testing with unknown dataset at different sampling rates. Neural network testing results showed that accuracy load identification can be achieved by using additional input features such as the TT-transform with best feature combination of real power, reactive power and TT-transform.

Original languageEnglish
Pages (from-to)10.1-10.6
JournalInternational Journal of Simulation: Systems, Science and Technology
Volume17
Issue number41
DOIs
Publication statusPublished - 2017

Fingerprint

Mathematical transformations
Monitoring
Neural Networks
Transform
Neural networks
Smart meters
Reactive power
Feature extraction
Sampling
Testing
Multilayer neural networks
Feature Extraction
Backpropagation
Personal computers
Lighting
Back-propagation Neural Network
Personal Computer
Perceptron
Impedance
Air

Keywords

  • Load recognition
  • Multilayer perceptron backpropagation artificial neural network (MLP-BPNN)
  • Nonintrusive load monitoring (NILM)
  • S-transform
  • Smart meter
  • Time-time transform (TT-transform)

ASJC Scopus subject areas

  • Software
  • Modelling and Simulation

Cite this

Nonintrusive load monitoring using TT-transform and neural networks. / Khalid, Khairuddin; Mohamed, Azah; Shareef, Hussain.

In: International Journal of Simulation: Systems, Science and Technology, Vol. 17, No. 41, 2017, p. 10.1-10.6.

Research output: Contribution to journalArticle

Khalid, Khairuddin ; Mohamed, Azah ; Shareef, Hussain. / Nonintrusive load monitoring using TT-transform and neural networks. In: International Journal of Simulation: Systems, Science and Technology. 2017 ; Vol. 17, No. 41. pp. 10.1-10.6.
@article{eb1f812bd5094538ade24c61cdb4653a,
title = "Nonintrusive load monitoring using TT-transform and neural networks",
abstract = "This paper presents nonintrusive load monitoring (NILM) method using the TT-transform feature extraction technique and multilayer perceptron with back-propagation neural network. The low sampling rate of load data were measured by using a smart meter to provide information on the operation of the loads such as air conditioner, personal computer and lighting. The accuracy of load identification with event based method is dependent on the measured signals and the selected features. To improve the identification of various types of loads, the TT-transform feature extraction technique is applied so as to provide additional features for characterizing the loads. Based on the load data obtained from the smart meter, the different features extracted such as real power, reactive power, power factor, apparent power, impedance, event signal (ΔP) and TT-transform features. These features are used as inputs to MLP-BPNN for identifying the various types of loads. The neural network is validated by testing with unknown dataset at different sampling rates. Neural network testing results showed that accuracy load identification can be achieved by using additional input features such as the TT-transform with best feature combination of real power, reactive power and TT-transform.",
keywords = "Load recognition, Multilayer perceptron backpropagation artificial neural network (MLP-BPNN), Nonintrusive load monitoring (NILM), S-transform, Smart meter, Time-time transform (TT-transform)",
author = "Khairuddin Khalid and Azah Mohamed and Hussain Shareef",
year = "2017",
doi = "10.5013/IJSSST.a.17.41.10",
language = "English",
volume = "17",
pages = "10.1--10.6",
journal = "International Journal of Simulation: Systems, Science and Technology",
issn = "1473-804X",
publisher = "United Kingdom Simulation Society",
number = "41",

}

TY - JOUR

T1 - Nonintrusive load monitoring using TT-transform and neural networks

AU - Khalid, Khairuddin

AU - Mohamed, Azah

AU - Shareef, Hussain

PY - 2017

Y1 - 2017

N2 - This paper presents nonintrusive load monitoring (NILM) method using the TT-transform feature extraction technique and multilayer perceptron with back-propagation neural network. The low sampling rate of load data were measured by using a smart meter to provide information on the operation of the loads such as air conditioner, personal computer and lighting. The accuracy of load identification with event based method is dependent on the measured signals and the selected features. To improve the identification of various types of loads, the TT-transform feature extraction technique is applied so as to provide additional features for characterizing the loads. Based on the load data obtained from the smart meter, the different features extracted such as real power, reactive power, power factor, apparent power, impedance, event signal (ΔP) and TT-transform features. These features are used as inputs to MLP-BPNN for identifying the various types of loads. The neural network is validated by testing with unknown dataset at different sampling rates. Neural network testing results showed that accuracy load identification can be achieved by using additional input features such as the TT-transform with best feature combination of real power, reactive power and TT-transform.

AB - This paper presents nonintrusive load monitoring (NILM) method using the TT-transform feature extraction technique and multilayer perceptron with back-propagation neural network. The low sampling rate of load data were measured by using a smart meter to provide information on the operation of the loads such as air conditioner, personal computer and lighting. The accuracy of load identification with event based method is dependent on the measured signals and the selected features. To improve the identification of various types of loads, the TT-transform feature extraction technique is applied so as to provide additional features for characterizing the loads. Based on the load data obtained from the smart meter, the different features extracted such as real power, reactive power, power factor, apparent power, impedance, event signal (ΔP) and TT-transform features. These features are used as inputs to MLP-BPNN for identifying the various types of loads. The neural network is validated by testing with unknown dataset at different sampling rates. Neural network testing results showed that accuracy load identification can be achieved by using additional input features such as the TT-transform with best feature combination of real power, reactive power and TT-transform.

KW - Load recognition

KW - Multilayer perceptron backpropagation artificial neural network (MLP-BPNN)

KW - Nonintrusive load monitoring (NILM)

KW - S-transform

KW - Smart meter

KW - Time-time transform (TT-transform)

UR - http://www.scopus.com/inward/record.url?scp=85017281191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017281191&partnerID=8YFLogxK

U2 - 10.5013/IJSSST.a.17.41.10

DO - 10.5013/IJSSST.a.17.41.10

M3 - Article

AN - SCOPUS:85017281191

VL - 17

SP - 10.1-10.6

JO - International Journal of Simulation: Systems, Science and Technology

JF - International Journal of Simulation: Systems, Science and Technology

SN - 1473-804X

IS - 41

ER -