Artificial neural network for non-intrusive electrical energy monitoring system
This paper discusses non-intrusive electrical energy monitoring (NIEM) system in an effort to minimize electrical energy wastages. To realize the system, an energy meter is used to measure the electrical consumption by electrical appliances. The obtained data were analyzed using a method called mult...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Advanced Engineering and Science
2017
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/74880/1/MohdAmriYunus2017_ArtificialNeuralNetworkforNon-IntrusiveElectrica.pdf http://eprints.utm.my/id/eprint/74880/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019628637&doi=10.11591%2fijeecs.v6.i1.pp124-131&partnerID=40&md5=b61291a2f2be562f8d09d0f89b4a0cca |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.74880 |
---|---|
record_format |
eprints |
spelling |
my.utm.748802018-03-21T00:29:03Z http://eprints.utm.my/id/eprint/74880/ Artificial neural network for non-intrusive electrical energy monitoring system Kaman, K. K. Faramarzi, M. Ibrahim, S. Yunus, M. A. M. TK Electrical engineering. Electronics Nuclear engineering This paper discusses non-intrusive electrical energy monitoring (NIEM) system in an effort to minimize electrical energy wastages. To realize the system, an energy meter is used to measure the electrical consumption by electrical appliances. The obtained data were analyzed using a method called multilayer perceptron (MLP) technique of artificial neural network (ANN). The event detection was implemented to identify the type of loads and the power consumption of the load which were identified as fan and lamp. The switching ON and OFF output events of the loads were inputted to MLP in order to test the capability of MLP in classifying the type of loads. The data were divided to 70% for training, 15% for testing, and 15% for validation. The output of the MLP is either ‘1’ for fan or ‘0’ for lamp. In conclusion, MLP with five hidden neurons results obtained the lowest average training time with 2.699 seconds, a small number of epochs with 62 iterations, a min square error of 7.3872×10-5, and a high regression coefficient of 0.99050. Institute of Advanced Engineering and Science 2017 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/74880/1/MohdAmriYunus2017_ArtificialNeuralNetworkforNon-IntrusiveElectrica.pdf Kaman, K. K. and Faramarzi, M. and Ibrahim, S. and Yunus, M. A. M. (2017) Artificial neural network for non-intrusive electrical energy monitoring system. Indonesian Journal of Electrical Engineering and Computer Science, 6 (1). pp. 124-131. ISSN 2502-4752 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019628637&doi=10.11591%2fijeecs.v6.i1.pp124-131&partnerID=40&md5=b61291a2f2be562f8d09d0f89b4a0cca DOI:10.11591/ijeecs.v6.i1.pp124-131 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Kaman, K. K. Faramarzi, M. Ibrahim, S. Yunus, M. A. M. Artificial neural network for non-intrusive electrical energy monitoring system |
description |
This paper discusses non-intrusive electrical energy monitoring (NIEM) system in an effort to minimize electrical energy wastages. To realize the system, an energy meter is used to measure the electrical consumption by electrical appliances. The obtained data were analyzed using a method called multilayer perceptron (MLP) technique of artificial neural network (ANN). The event detection was implemented to identify the type of loads and the power consumption of the load which were identified as fan and lamp. The switching ON and OFF output events of the loads were inputted to MLP in order to test the capability of MLP in classifying the type of loads. The data were divided to 70% for training, 15% for testing, and 15% for validation. The output of the MLP is either ‘1’ for fan or ‘0’ for lamp. In conclusion, MLP with five hidden neurons results obtained the lowest average training time with 2.699 seconds, a small number of epochs with 62 iterations, a min square error of 7.3872×10-5, and a high regression coefficient of 0.99050. |
format |
Article |
author |
Kaman, K. K. Faramarzi, M. Ibrahim, S. Yunus, M. A. M. |
author_facet |
Kaman, K. K. Faramarzi, M. Ibrahim, S. Yunus, M. A. M. |
author_sort |
Kaman, K. K. |
title |
Artificial neural network for non-intrusive electrical energy monitoring system |
title_short |
Artificial neural network for non-intrusive electrical energy monitoring system |
title_full |
Artificial neural network for non-intrusive electrical energy monitoring system |
title_fullStr |
Artificial neural network for non-intrusive electrical energy monitoring system |
title_full_unstemmed |
Artificial neural network for non-intrusive electrical energy monitoring system |
title_sort |
artificial neural network for non-intrusive electrical energy monitoring system |
publisher |
Institute of Advanced Engineering and Science |
publishDate |
2017 |
url |
http://eprints.utm.my/id/eprint/74880/1/MohdAmriYunus2017_ArtificialNeuralNetworkforNon-IntrusiveElectrica.pdf http://eprints.utm.my/id/eprint/74880/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019628637&doi=10.11591%2fijeecs.v6.i1.pp124-131&partnerID=40&md5=b61291a2f2be562f8d09d0f89b4a0cca |
_version_ |
1643656960102367232 |
score |
13.18916 |