Dimension reduction for NILM classification based on principle component analysis

Ram Machlev; Dmitri Tolkachov; Yoash Levron; Yuval Beck

doi:10.1016/j.epsr.2020.106459

Dimension reduction for NILM classification based on principle component analysis

Ram Machlev^*, Dmitri Tolkachov, Yoash Levron, Yuval Beck

^*Corresponding author for this work

School of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

33 Scopus citations

Abstract

Non-intrusive load monitoring (NILM) techniques estimate the consumption of individual appliances in a household or facility, based on readings of a centralized meter. Usually, NILM techniques are shown to be improved when various power features and additional power quality parameters are included. However, adding power features leads to increased time complexity which is a disadvantage to real-time operation. Therefore, in this work we offer a process based on principal component analysis (PCA) which reduces the dimension of NILM power features. The suggested method can be used with any NILM classification technique, and shows good performance in terms of standard measures and time complexity when tested on popular datasets.

Original language	English
Article number	106459
Journal	Electric Power Systems Research
Volume	187
DOIs	https://doi.org/10.1016/j.epsr.2020.106459
State	Published - Oct 2020

Funding

Funders	Funder number
Israel Science Foundation	2//7221
Israeli Innovation Authority	60689
SATEC Ltd.

Keywords

Classification
Non-intrusive load monitoring (NILM)
Power features
Principal component analysis (PCA)
Smart meter

Access to Document

10.1016/j.epsr.2020.106459

Cite this

@article{827152e81bde4fedb1dbc3e82702e413,

title = "Dimension reduction for NILM classification based on principle component analysis",

abstract = "Non-intrusive load monitoring (NILM) techniques estimate the consumption of individual appliances in a household or facility, based on readings of a centralized meter. Usually, NILM techniques are shown to be improved when various power features and additional power quality parameters are included. However, adding power features leads to increased time complexity which is a disadvantage to real-time operation. Therefore, in this work we offer a process based on principal component analysis (PCA) which reduces the dimension of NILM power features. The suggested method can be used with any NILM classification technique, and shows good performance in terms of standard measures and time complexity when tested on popular datasets.",

keywords = "Classification, Non-intrusive load monitoring (NILM), Power features, Principal component analysis (PCA), Smart meter",

author = "Ram Machlev and Dmitri Tolkachov and Yoash Levron and Yuval Beck",

note = "Publisher Copyright: {\textcopyright} 2020 Elsevier B.V.",

year = "2020",

month = oct,

doi = "10.1016/j.epsr.2020.106459",

language = "אנגלית",

volume = "187",

journal = "Electric Power Systems Research",

issn = "0378-7796",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Dimension reduction for NILM classification based on principle component analysis

AU - Machlev, Ram

AU - Tolkachov, Dmitri

AU - Levron, Yoash

AU - Beck, Yuval

PY - 2020/10

Y1 - 2020/10

N2 - Non-intrusive load monitoring (NILM) techniques estimate the consumption of individual appliances in a household or facility, based on readings of a centralized meter. Usually, NILM techniques are shown to be improved when various power features and additional power quality parameters are included. However, adding power features leads to increased time complexity which is a disadvantage to real-time operation. Therefore, in this work we offer a process based on principal component analysis (PCA) which reduces the dimension of NILM power features. The suggested method can be used with any NILM classification technique, and shows good performance in terms of standard measures and time complexity when tested on popular datasets.

AB - Non-intrusive load monitoring (NILM) techniques estimate the consumption of individual appliances in a household or facility, based on readings of a centralized meter. Usually, NILM techniques are shown to be improved when various power features and additional power quality parameters are included. However, adding power features leads to increased time complexity which is a disadvantage to real-time operation. Therefore, in this work we offer a process based on principal component analysis (PCA) which reduces the dimension of NILM power features. The suggested method can be used with any NILM classification technique, and shows good performance in terms of standard measures and time complexity when tested on popular datasets.

KW - Classification

KW - Non-intrusive load monitoring (NILM)

KW - Power features

KW - Principal component analysis (PCA)

KW - Smart meter

UR - http://www.scopus.com/inward/record.url?scp=85086453160&partnerID=8YFLogxK

U2 - 10.1016/j.epsr.2020.106459

DO - 10.1016/j.epsr.2020.106459

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85086453160

SN - 0378-7796

VL - 187

JO - Electric Power Systems Research

JF - Electric Power Systems Research

M1 - 106459

ER -

Dimension reduction for NILM classification based on principle component analysis

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this