Blind non-intrusive appliance load monitoring using graph-based signal processing

Research output: Contribution to conferencePaper

Abstract

With ongoing massive smart energy metering deployments, disaggregation of household's total energy consumption down to individual appliances using purely software tools, aka. non-intrusive appliance load monitoring (NALM), has generated increased interest. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges. Indeed, the majority of approaches require training and are sensitive to appliance changes requiring regular re-training. In this paper, we tackle this challenge by proposing a 'blind' NALM approach that does not require any training. The main idea is to build upon an emerging field of graph-based signal processing to perform adaptive threshold-ing, signal clustering and feature matching. Using two datasets of active power measurements with 1min and 8sec resolution, we demonstrate the effectiveness of the proposed method using a state-of-the-art NALM approaches as benchmarks.
LanguageEnglish
Number of pages5
StatePublished - Dec 2015
EventGLOBALSIP-2015 - FL, Orlando, United States
Duration: 14 Dec 201516 Dec 2015

Conference

ConferenceGLOBALSIP-2015
CountryUnited States
CityOrlando
Period14/12/1516/12/15

Fingerprint

Signal processing
Monitoring
Energy utilization

Keywords

  • load disaggregation
  • graph-based signal processing
  • non-intrusive appliance load monitoring

Cite this

@conference{3a3cabdab2994047b83a5b75dce45144,
title = "Blind non-intrusive appliance load monitoring using graph-based signal processing",
abstract = "With ongoing massive smart energy metering deployments, disaggregation of household's total energy consumption down to individual appliances using purely software tools, aka. non-intrusive appliance load monitoring (NALM), has generated increased interest. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges. Indeed, the majority of approaches require training and are sensitive to appliance changes requiring regular re-training. In this paper, we tackle this challenge by proposing a 'blind' NALM approach that does not require any training. The main idea is to build upon an emerging field of graph-based signal processing to perform adaptive threshold-ing, signal clustering and feature matching. Using two datasets of active power measurements with 1min and 8sec resolution, we demonstrate the effectiveness of the proposed method using a state-of-the-art NALM approaches as benchmarks.",
keywords = "load disaggregation, graph-based signal processing, non-intrusive appliance load monitoring",
author = "Bochao Zhao and Lina Stankovic and Vladimir Stankovic",
year = "2015",
month = "12",
language = "English",
note = "GLOBALSIP-2015 ; Conference date: 14-12-2015 Through 16-12-2015",

}

Zhao, B, Stankovic, L & Stankovic, V 2015, 'Blind non-intrusive appliance load monitoring using graph-based signal processing' Paper presented at GLOBALSIP-2015, Orlando, United States, 14/12/15 - 16/12/15, .

Blind non-intrusive appliance load monitoring using graph-based signal processing. / Zhao, Bochao; Stankovic, Lina; Stankovic, Vladimir.

2015. Paper presented at GLOBALSIP-2015, Orlando, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Blind non-intrusive appliance load monitoring using graph-based signal processing

AU - Zhao,Bochao

AU - Stankovic,Lina

AU - Stankovic,Vladimir

PY - 2015/12

Y1 - 2015/12

N2 - With ongoing massive smart energy metering deployments, disaggregation of household's total energy consumption down to individual appliances using purely software tools, aka. non-intrusive appliance load monitoring (NALM), has generated increased interest. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges. Indeed, the majority of approaches require training and are sensitive to appliance changes requiring regular re-training. In this paper, we tackle this challenge by proposing a 'blind' NALM approach that does not require any training. The main idea is to build upon an emerging field of graph-based signal processing to perform adaptive threshold-ing, signal clustering and feature matching. Using two datasets of active power measurements with 1min and 8sec resolution, we demonstrate the effectiveness of the proposed method using a state-of-the-art NALM approaches as benchmarks.

AB - With ongoing massive smart energy metering deployments, disaggregation of household's total energy consumption down to individual appliances using purely software tools, aka. non-intrusive appliance load monitoring (NALM), has generated increased interest. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges. Indeed, the majority of approaches require training and are sensitive to appliance changes requiring regular re-training. In this paper, we tackle this challenge by proposing a 'blind' NALM approach that does not require any training. The main idea is to build upon an emerging field of graph-based signal processing to perform adaptive threshold-ing, signal clustering and feature matching. Using two datasets of active power measurements with 1min and 8sec resolution, we demonstrate the effectiveness of the proposed method using a state-of-the-art NALM approaches as benchmarks.

KW - load disaggregation

KW - graph-based signal processing

KW - non-intrusive appliance load monitoring

UR - http://2015.ieeeglobalsip.org/

M3 - Paper

ER -