research-article

An unsupervised load disaggregation approach based on graph signal processing featuring power sequences

Authors:

Xuhao Li,

Bochao Zhao,

Wenpeng Luan,

Bo LiuAuthors Info & Claims

BuildSys '22: Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Pages 378 - 382

https://doi.org/10.1145/3563357.3566156

Published: 08 December 2022 Publication History

Get Access

Abstract

Non-intrusive load monitoring (NILM) offers appliance-level electricity usage details via analysing aggregate power readings. Although graph signal processing (GSP) concepts have been applied to load disaggregation from low-rate power measurements in an unsupervised manner, the robustness of GSP-based NILM solutions can be enhanced by improving feature selection. In this paper, a method is proposed for extracting state transition sequence (STS) features from power readings, instead of power changes and steady-state power sequences featured in the existing works. By building a graph for the extracted STSs, clustering can be performed, where dynamic time warping is used to calculate correlation between STSs. Finally, the grouped STSs is matched for performing load disaggregation. Experiments are carried out on publicly-accessible AMPds and REFIT datasets, showing the proposed method generally outperforms two state-of-the-art benchmarks in various evaluation metrics.

References

[1]

George William Hart. Nonintrusive appliance load monitoring. Proceedings of the IEEE, 80(12):1870--1891, 1992.

Crossref

Google Scholar

[2]

Xuhao Li, Bochao Zhao, Wenpeng Luan, and Bo Liu. A training-free non-intrusive load monitoring approach for high-frequency measurements based on graph signal processing. In 2022 7th Asia Conference on Power and Electrical Engineering (ACPEE), pages 859--863, 2022.

Crossref

Google Scholar

[3]

Stephen Makonin, Fred Popowich, Ivan V Bajić, Bob Gill, and Lyn Bartram. Exploiting hmm sparsity to perform online real-time nonintrusive load monitoring. IEEE Transactions on smart grid, 7(6):2575--2585, 2015.

Crossref

Google Scholar

[4]

Ziwei Xiao, Wenjie Gang, Jiaqi Yuan, Ying Zhang, and Cheng Fan. Cooling load disaggregation using a nilm method based on random forest for smart buildings. Sustainable Cities and Society, 74:103202, 2021.

Crossref

Google Scholar

[5]

Jack Kelly and William Knottenbelt. Neural nilm: Deep neural networks applied to energy disaggregation. In Proceedings of the 2nd ACM international conference on embedded systems for energy-efficient built environments, pages 55--64, 2015.

Digital Library

Google Scholar

[6]

Bochao Zhao, Lina Stankovic, and Vladimir Stankovic. On a training-less solution for non-intrusive appliance load monitoring using graph signal processing. IEEE Access, 4:1784--1799, 2016.

Crossref

Google Scholar

[7]

Kanghang He, Vladimir Stankovic, and Lina Stankovic. Building a graph signal processing model using dynamic time warping for load disaggregation. Sensors, 20(22):6628, 2020.

Crossref

Google Scholar

[8]

Chaoyun Zhang, Mingjun Zhong, Zongzuo Wang, Nigel Goddard, and Charles Sutton. Sequence-to-point learning with neural networks for non-intrusive load monitoring. In Thirty-second AAAI conference on artificial intelligence, 2018.

Crossref

Google Scholar

[9]

Michele D'Incecco, Stefano Squartini, and Mingjun Zhong. Transfer learning for non-intrusive load monitoring. IEEE Transactions on Smart Grid, 11(2):1419--1429, 2019.

Crossref

Google Scholar

[10]

Vladimir Stankovic, Jing Liao, and Lina Stankovic. A graph-based signal processing approach for low-rate energy disaggregation. In 2014 IEEE symposium on computational intelligence for engineering solutions (CIES), pages 81--87. IEEE, 2014.

Crossref

Google Scholar

[11]

Kanghang He, Lina Stankovic, Jing Liao, and Vladimir Stankovic. Non-intrusive load disaggregation using graph signal processing. IEEE Transactions on Smart Grid, 9(3):1739--1747, 2018.

Crossref

Google Scholar

[12]

Bochao Zhao, Kanghang He, Lina Stankovic, and Vladimir Stankovic. Improving event-based non-intrusive load monitoring using graph signal processing. IEEE Access, PP(99):1--1, 2018.

Crossref

Google Scholar

[13]

Stephen Makonin, Bradley Ellert, Ivan V. Bajic, and Fred Popowich. Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014. Scientific Data, 3(160037):1--12, 2016.

Google Scholar

[14]

David Murray, Lina Stankovic, and Vladimir Stankovic. An electrical load measurements dataset of united kingdom households from a two-year longitudinal study. Scientific Data, 4:160122, 2017.

Crossref

Google Scholar

Cited By

View all

Zhao BLi XLuan WLiu B(2023)Apply Graph Signal Processing on NILM: An Unsupervised Approach Featuring Power SequencesSensors10.3390/s2308393923:8(3939)Online publication date: 12-Apr-2023
https://doi.org/10.3390/s23083939
Pujić DTomašević NBatić M(2023)A Semi-Supervised Approach for Improving Generalization in Non-Intrusive Load MonitoringSensors10.3390/s2303144423:3(1444)Online publication date: 28-Jan-2023
https://doi.org/10.3390/s23031444
Ghaffar MSheikh SNaseer NUsama SSalah BAlkhatib S(2023)Accuracy Improvement of Non-Intrusive Load Monitoring Using Voting-Based Consensus ClusteringIEEE Access10.1109/ACCESS.2023.3279489(1-1)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3279489

Index Terms

An unsupervised load disaggregation approach based on graph signal processing featuring power sequences
1. Information systems
  1. Information systems applications
    1. Data mining
      1. Clustering

Recommendations

A feature extraction model based on discriminative graph signals
Highlights
- Propose the idea of discriminative graph signal.
- Propose a feature extraction ...
Abstract
Classification finds wide applications in artificial intelligence and expert systems. Feature extraction is a key step for classifier learning. However, the relation among samples is usually ignored in classical feature extraction ...
Home electrical signal disaggregation for non-intrusive load monitoring (NILM) systems

Electrical load disaggregation for end-use recognition in the smart home has become an area of study of its own right. The most well-known examples are energy monitoring, health care applications, in-home activity modeling, and home automation. Real-...
A new graph learning-based signal processing approach for non-intrusive load disaggregation with active power measurements
Abstract
Recently, there is a potential technology called graph-based signal processing (GSP) that is being used in many applications. GSP has been used successfully in the domains such as signal and image filtering and processing. In the paper, GSP is ...

Comments

Information & Contributors

Information

Published In

BuildSys '22: Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

November 2022

535 pages

ISBN:9781450398909

DOI:10.1145/3563357

General Chair:
Jorge Ortiz
Rutgers University

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 December 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

BuildSys '22

Sponsor:

SIGEnergy

BuildSys '22: The 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

November 9 - 10, 2022

Massachusetts, Boston

Acceptance Rates

Overall Acceptance Rate 148 of 500 submissions, 30%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
51
Total Downloads

Downloads (Last 12 months)17
Downloads (Last 6 weeks)6

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Zhao BLi XLuan WLiu B(2023)Apply Graph Signal Processing on NILM: An Unsupervised Approach Featuring Power SequencesSensors10.3390/s2308393923:8(3939)Online publication date: 12-Apr-2023
https://doi.org/10.3390/s23083939
Pujić DTomašević NBatić M(2023)A Semi-Supervised Approach for Improving Generalization in Non-Intrusive Load MonitoringSensors10.3390/s2303144423:3(1444)Online publication date: 28-Jan-2023
https://doi.org/10.3390/s23031444
Ghaffar MSheikh SNaseer NUsama SSalah BAlkhatib S(2023)Accuracy Improvement of Non-Intrusive Load Monitoring Using Voting-Based Consensus ClusteringIEEE Access10.1109/ACCESS.2023.3279489(1-1)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3279489

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Abstract

References

Cited By

Index Terms

Recommendations

A feature extraction model based on discriminative graph signals

Home electrical signal disaggregation for non-intrusive load monitoring (NILM) systems

A new graph learning-based signal processing approach for non-intrusive load disaggregation with active power measurements

Comments

Information

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Share

Share this Publication link

Share on social media

Affiliations