A novel feature extraction and classification algorithm based on power components using single-point monitoring for NILM

Author

Nguyen, M. ; Alshareef, S. ; Gilani, A. ; Morsi, W.G.

fYear

2015

fDate

3-6 May 2015

Firstpage

37

Lastpage

40

Abstract

This paper presents a classification approach based on the power components and applied to the Non-Intrusive Load Monitoring (NILM). The active, reactive and apparent power levels are recorded and are fed to a Decision Tree (DT) classifier to develop the appropriate classification model. The results have shown that using the change in the power components level instead of using the actual power components recorded can result in significant improvement in the classification accuracy.

Keywords

decision trees; feature extraction; load management; pattern classification; power apparatus; power engineering computing; reactive power; DT classifier; NILM; active power level; apparent power level; classification model; decision tree classifier; nonintrusive load monitoring; power components; reactive power level; single-point monitoring; Accuracy; Computational modeling; Decision trees; Load modeling; Monitoring; Power measurement; Switches; Decision Tree classification; non-intrusive load monitoring; power components;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering (CCECE), 2015 IEEE 28th Canadian Conference on

Conference_Location

Halifax, NS

ISSN

0840-7789

Print_ISBN

978-1-4799-5827-6

Type

conf

DOI

10.1109/CCECE.2015.7129156

Filename

7129156