Nonintrusive load identification using extreme learning machine and TT-transform

Khairuddin Khalid, Azah Mohamed, Ramizi Mohamed, Hussain Shareef

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper presents a new nonintrusive load identification method to disaggregate the target load in a typical commercial building. For this purpose, experiments were carried out in the laboratory implementing real load switching activity and power measurements were made with a smart meter. Nonintrusive load monitoring is performed by analysing the power signals obtained from the smart meter and detecting the operation of load appliances. A new feature extraction technique based on the time-time (TT)-transform is applied to improve the load identification. For classifying and predicting the various load operations, a new intelligent technique called as extreme learning machine with single hidden layer feedforward neural network is developed. ELM has high efficiency and simple to be implemented. The inputs to the ELM are the extracted TT-transform features together with other signals like real and reactive powers while the ELM outputs are the switching states of the load appliances. The load appliances considered in the study are the lightings, personal computers and air conditioners. The ELM accuracy is validated by testing with unknown dataset recorded by the smart meter at 1 minute sampling rate. The ELM testing results showed that the desired level of load identification can be achieved by using additional TT-transform features.

Original languageEnglish
Title of host publication2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages271-276
Number of pages6
ISBN (Electronic)9781509028894
DOIs
Publication statusPublished - 27 Mar 2017
Event2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016 - Putrajaya, Malaysia
Duration: 14 Nov 201616 Nov 2016

Other

Other2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016
CountryMalaysia
CityPutrajaya
Period14/11/1616/11/16

Fingerprint

Smart meters
machine learning
Learning systems
Identification (control systems)
Mathematical transformations
Feedforward neural networks
Testing
Reactive power
Personal computers
Feature extraction
Lighting
Sampling
Monitoring
Air
Experiments
personal computers
classifying
pattern recognition
illuminating
sampling

Keywords

  • Extreme learning machine
  • Feature extraction
  • Nonintrusive load monitoring
  • TT-transform

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Biomedical Engineering
  • Control and Systems Engineering
  • Hardware and Architecture
  • Computer Networks and Communications
  • Instrumentation

Cite this

Khalid, K., Mohamed, A., Mohamed, R., & Shareef, H. (2017). Nonintrusive load identification using extreme learning machine and TT-transform. In 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016 (pp. 271-276). [7888051] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAEES.2016.7888051

Nonintrusive load identification using extreme learning machine and TT-transform. / Khalid, Khairuddin; Mohamed, Azah; Mohamed, Ramizi; Shareef, Hussain.

2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 271-276 7888051.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Khalid, K, Mohamed, A, Mohamed, R & Shareef, H 2017, Nonintrusive load identification using extreme learning machine and TT-transform. in 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016., 7888051, Institute of Electrical and Electronics Engineers Inc., pp. 271-276, 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016, Putrajaya, Malaysia, 14/11/16. https://doi.org/10.1109/ICAEES.2016.7888051
Khalid K, Mohamed A, Mohamed R, Shareef H. Nonintrusive load identification using extreme learning machine and TT-transform. In 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 271-276. 7888051 https://doi.org/10.1109/ICAEES.2016.7888051
Khalid, Khairuddin ; Mohamed, Azah ; Mohamed, Ramizi ; Shareef, Hussain. / Nonintrusive load identification using extreme learning machine and TT-transform. 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 271-276
@inproceedings{3b58146c2a614347a1d73e9ce4bda863,
title = "Nonintrusive load identification using extreme learning machine and TT-transform",
abstract = "This paper presents a new nonintrusive load identification method to disaggregate the target load in a typical commercial building. For this purpose, experiments were carried out in the laboratory implementing real load switching activity and power measurements were made with a smart meter. Nonintrusive load monitoring is performed by analysing the power signals obtained from the smart meter and detecting the operation of load appliances. A new feature extraction technique based on the time-time (TT)-transform is applied to improve the load identification. For classifying and predicting the various load operations, a new intelligent technique called as extreme learning machine with single hidden layer feedforward neural network is developed. ELM has high efficiency and simple to be implemented. The inputs to the ELM are the extracted TT-transform features together with other signals like real and reactive powers while the ELM outputs are the switching states of the load appliances. The load appliances considered in the study are the lightings, personal computers and air conditioners. The ELM accuracy is validated by testing with unknown dataset recorded by the smart meter at 1 minute sampling rate. The ELM testing results showed that the desired level of load identification can be achieved by using additional TT-transform features.",
keywords = "Extreme learning machine, Feature extraction, Nonintrusive load monitoring, TT-transform",
author = "Khairuddin Khalid and Azah Mohamed and Ramizi Mohamed and Hussain Shareef",
year = "2017",
month = "3",
day = "27",
doi = "10.1109/ICAEES.2016.7888051",
language = "English",
pages = "271--276",
booktitle = "2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Nonintrusive load identification using extreme learning machine and TT-transform

AU - Khalid, Khairuddin

AU - Mohamed, Azah

AU - Mohamed, Ramizi

AU - Shareef, Hussain

PY - 2017/3/27

Y1 - 2017/3/27

N2 - This paper presents a new nonintrusive load identification method to disaggregate the target load in a typical commercial building. For this purpose, experiments were carried out in the laboratory implementing real load switching activity and power measurements were made with a smart meter. Nonintrusive load monitoring is performed by analysing the power signals obtained from the smart meter and detecting the operation of load appliances. A new feature extraction technique based on the time-time (TT)-transform is applied to improve the load identification. For classifying and predicting the various load operations, a new intelligent technique called as extreme learning machine with single hidden layer feedforward neural network is developed. ELM has high efficiency and simple to be implemented. The inputs to the ELM are the extracted TT-transform features together with other signals like real and reactive powers while the ELM outputs are the switching states of the load appliances. The load appliances considered in the study are the lightings, personal computers and air conditioners. The ELM accuracy is validated by testing with unknown dataset recorded by the smart meter at 1 minute sampling rate. The ELM testing results showed that the desired level of load identification can be achieved by using additional TT-transform features.

AB - This paper presents a new nonintrusive load identification method to disaggregate the target load in a typical commercial building. For this purpose, experiments were carried out in the laboratory implementing real load switching activity and power measurements were made with a smart meter. Nonintrusive load monitoring is performed by analysing the power signals obtained from the smart meter and detecting the operation of load appliances. A new feature extraction technique based on the time-time (TT)-transform is applied to improve the load identification. For classifying and predicting the various load operations, a new intelligent technique called as extreme learning machine with single hidden layer feedforward neural network is developed. ELM has high efficiency and simple to be implemented. The inputs to the ELM are the extracted TT-transform features together with other signals like real and reactive powers while the ELM outputs are the switching states of the load appliances. The load appliances considered in the study are the lightings, personal computers and air conditioners. The ELM accuracy is validated by testing with unknown dataset recorded by the smart meter at 1 minute sampling rate. The ELM testing results showed that the desired level of load identification can be achieved by using additional TT-transform features.

KW - Extreme learning machine

KW - Feature extraction

KW - Nonintrusive load monitoring

KW - TT-transform

UR - http://www.scopus.com/inward/record.url?scp=85018166671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018166671&partnerID=8YFLogxK

U2 - 10.1109/ICAEES.2016.7888051

DO - 10.1109/ICAEES.2016.7888051

M3 - Conference contribution

SP - 271

EP - 276

BT - 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -