Electric Load Disaggregation in Smart Metering Using a Novel Feature Extraction Method and Supervised Classification

Improving energy efficiency by monitoring household electrical consumption is of significant importance with the present-day climate change concerns. A solution for the electrical consumption management problem is the use of a nonintrusive appliance load monitoring system. This system captures the s...

Full description

Saved in:
Bibliographic Details
Published in:Energy procedia 2011, Vol.6, p.627-632
Main Authors: Chahine, Khaled, Drissi, Khalil El Khamlichi, Pasquier, Christophe, Kerroum, Kamal, Faure, Claire, Jouannet, Thierry, Michou, Michel
Format: Article
Language:English
Subjects:
Matrix Pencil Method
Nonintrusive Appliance Load Monitoring
Power Saving
Smart Meters
Supervised Learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Improving energy efficiency by monitoring household electrical consumption is of significant importance with the present-day climate change concerns. A solution for the electrical consumption management problem is the use of a nonintrusive appliance load monitoring system. This system captures the signals from the aggregate consumption, extracts the features from these signals and classifies the extracted features in order to identify the switched on appliances. This paper complements a novel feature extraction scheme presented in a previous work for load disaggregation with a comparative study of supervised classification methods. The objective of the current work is hence to make use of the feature extraction scheme to construct a database of signatures and then to compare different supervised learning methods for load classification. Preliminary results indicate high classification accuracy of all tested methods.
ISSN:1876-6102
1876-6102
DOI:10.1016/j.egypro.2011.05.072