Improving event-based non-intrusive load monitoring using graph signal processing

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Large-scale smart energy metering deployment worldwide and integration of smart meters within the smart grid will enable two-way communication between the consumer and energy network, thus ensuring improved response to demand. Energy disaggregation or Non-intrusive load monitoring (NILM), namely disaggregation of the total metered electricity consumption down to individual appliances using purely algorithmic tools, is gaining popularity as an added-value that makes the most of meter data. However, NILM remains a challenging problem since NILM is susceptible to sensor noise, unknown load noise, transient spikes and fluctuations. In this paper, we tackle this problem using novel graph signal processing (GSP) concepts, applied at both, physical signal level via graph-based filtering and data level, via effective semi-supervised GSP-based feature matching. The proposed GSP-based method is generic and can be used to improve results of various event-based NILM approaches. We demonstrate significant improvement in performance using three state-of-the-art NILM methods, both supervised and unsupervised, and real-world active power consumption readings from the REDD and REFIT datasets, sampled at 1 and 8 seconds, respectively.
LanguageEnglish
Pages1-15
Number of pages15
JournalIEEE Access
Early online date20 Sep 2018
DOIs
Publication statusE-pub ahead of print - 20 Sep 2018

Fingerprint

Signal processing
Monitoring
Smart meters
Electric power utilization
Electricity
Communication
Sensors

Keywords

  • load disaggregation
  • non-Intrusive Load Monitoring
  • smart metering
  • graph signal processing

Cite this

@article{3aab4462017d42869a005f7249473faa,
title = "Improving event-based non-intrusive load monitoring using graph signal processing",
abstract = "Large-scale smart energy metering deployment worldwide and integration of smart meters within the smart grid will enable two-way communication between the consumer and energy network, thus ensuring improved response to demand. Energy disaggregation or Non-intrusive load monitoring (NILM), namely disaggregation of the total metered electricity consumption down to individual appliances using purely algorithmic tools, is gaining popularity as an added-value that makes the most of meter data. However, NILM remains a challenging problem since NILM is susceptible to sensor noise, unknown load noise, transient spikes and fluctuations. In this paper, we tackle this problem using novel graph signal processing (GSP) concepts, applied at both, physical signal level via graph-based filtering and data level, via effective semi-supervised GSP-based feature matching. The proposed GSP-based method is generic and can be used to improve results of various event-based NILM approaches. We demonstrate significant improvement in performance using three state-of-the-art NILM methods, both supervised and unsupervised, and real-world active power consumption readings from the REDD and REFIT datasets, sampled at 1 and 8 seconds, respectively.",
keywords = "load disaggregation, non-Intrusive Load Monitoring, smart metering, graph signal processing",
author = "Bochao Zhao and Kanghang He and Lina Stankovic and Vladimir Stankovic",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2018",
month = "9",
day = "20",
doi = "10.1109/ACCESS.2018.2871343",
language = "English",
pages = "1--15",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

TY - JOUR

T1 - Improving event-based non-intrusive load monitoring using graph signal processing

AU - Zhao, Bochao

AU - He, Kanghang

AU - Stankovic, Lina

AU - Stankovic, Vladimir

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/9/20

Y1 - 2018/9/20

N2 - Large-scale smart energy metering deployment worldwide and integration of smart meters within the smart grid will enable two-way communication between the consumer and energy network, thus ensuring improved response to demand. Energy disaggregation or Non-intrusive load monitoring (NILM), namely disaggregation of the total metered electricity consumption down to individual appliances using purely algorithmic tools, is gaining popularity as an added-value that makes the most of meter data. However, NILM remains a challenging problem since NILM is susceptible to sensor noise, unknown load noise, transient spikes and fluctuations. In this paper, we tackle this problem using novel graph signal processing (GSP) concepts, applied at both, physical signal level via graph-based filtering and data level, via effective semi-supervised GSP-based feature matching. The proposed GSP-based method is generic and can be used to improve results of various event-based NILM approaches. We demonstrate significant improvement in performance using three state-of-the-art NILM methods, both supervised and unsupervised, and real-world active power consumption readings from the REDD and REFIT datasets, sampled at 1 and 8 seconds, respectively.

AB - Large-scale smart energy metering deployment worldwide and integration of smart meters within the smart grid will enable two-way communication between the consumer and energy network, thus ensuring improved response to demand. Energy disaggregation or Non-intrusive load monitoring (NILM), namely disaggregation of the total metered electricity consumption down to individual appliances using purely algorithmic tools, is gaining popularity as an added-value that makes the most of meter data. However, NILM remains a challenging problem since NILM is susceptible to sensor noise, unknown load noise, transient spikes and fluctuations. In this paper, we tackle this problem using novel graph signal processing (GSP) concepts, applied at both, physical signal level via graph-based filtering and data level, via effective semi-supervised GSP-based feature matching. The proposed GSP-based method is generic and can be used to improve results of various event-based NILM approaches. We demonstrate significant improvement in performance using three state-of-the-art NILM methods, both supervised and unsupervised, and real-world active power consumption readings from the REDD and REFIT datasets, sampled at 1 and 8 seconds, respectively.

KW - load disaggregation

KW - non-Intrusive Load Monitoring

KW - smart metering

KW - graph signal processing

UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639

U2 - 10.1109/ACCESS.2018.2871343

DO - 10.1109/ACCESS.2018.2871343

M3 - Article

SP - 1

EP - 15

JO - IEEE Access

T2 - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -