Path signatures for non-intrusive load monitoring

Paul Moore; Theodor-Mihai  Iliant; Filip-Alexandru  Ion; Yue Wu; Terry Lyons

doi:10.1109/ICASSP43922.2022.9747285

Path signatures for non-intrusive load monitoring

Paul Moore, Theodor-Mihai Iliant, Filip-Alexandru Ion, Yue Wu, Terry Lyons

Mathematics And Statistics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

2 Citations (Scopus)

61 Downloads (Pure)

Abstract

Non-intrusive load monitoring (NILM) is the analysis of electricity loads by means of a single supply wire, so avoiding separate monitors on individual appliances. Some approaches to NILM use the V-I trajectory for feature generation but they apply ad-hoc rules to generate the feature vector. This paper demonstrates a systematic method of feature generation called the path signature which has recently been applied in machine learning, often with notable success. We show how the path signature generates features from the V-I trajectory to give a test set accuracy of 98.81% on the COOLL dataset. We conclude that the path signature is easier to use and generalize than ad-hoc features, and it can be applied to many other applications which use multivariate sequential data.

Original language	English
Title of host publication	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Place of Publication	New York, N.Y.
Publisher	IEEE
Pages	3808-3812
Number of pages	5
ISBN (Electronic)	9781665405409
ISBN (Print)	9781665405416
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9747285
Publication status	Published - 27 May 2022
Event	2022 IEEE International Conference on Acoustics, Speech and Signal Processing - Marina Bay Sands Expo & Convention Center, Singapore, Singapore Duration: 22 May 2022 → 27 May 2022 https://2022.ieeeicassp.org/

Publication series

Name	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	IEEE

Conference

Conference	2022 IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	IEEE ICASSP 2022
Country/Territory	Singapore
City	Singapore
Period	22/05/22 → 27/05/22
Internet address	https://2022.ieeeicassp.org/

Keywords

non-intrusive load monitoring
disaggregation
machine learning
feature selection
path signatures

Access to Document

10.1109/ICASSP43922.2022.9747285

Moore-etal-ICASSP-2022-Path-signatures-for-non-intrusive-load-monitoringAccepted author manuscript, 647 KBLicence: Strath_1

Cite this

Moore, P., Iliant, T.-M., Ion, F.-A., Wu, Y., & Lyons, T. (2022). Path signatures for non-intrusive load monitoring. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3808-3812). (ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). IEEE. https://doi.org/10.1109/ICASSP43922.2022.9747285

@inproceedings{8a89cc75e76b418fa734c927cbec3dac,

title = "Path signatures for non-intrusive load monitoring",

abstract = "Non-intrusive load monitoring (NILM) is the analysis of electricity loads by means of a single supply wire, so avoiding separate monitors on individual appliances. Some approaches to NILM use the V-I trajectory for feature generation but they apply ad-hoc rules to generate the feature vector. This paper demonstrates a systematic method of feature generation called the path signature which has recently been applied in machine learning, often with notable success. We show how the path signature generates features from the V-I trajectory to give a test set accuracy of 98.81% on the COOLL dataset. We conclude that the path signature is easier to use and generalize than ad-hoc features, and it can be applied to many other applications which use multivariate sequential data.",

keywords = "non-intrusive load monitoring, disaggregation, machine learning, feature selection, path signatures",

author = "Paul Moore and Theodor-Mihai Iliant and Filip-Alexandru Ion and Yue Wu and Terry Lyons",

note = "{\textcopyright} 2022 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.; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE ICASSP 2022 ; Conference date: 22-05-2022 Through 27-05-2022",

year = "2022",

month = may,

day = "27",

doi = "10.1109/ICASSP43922.2022.9747285",

language = "English",

isbn = "9781665405416",

series = "ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

publisher = "IEEE",

pages = "3808--3812",

booktitle = "ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

url = "https://2022.ieeeicassp.org/",

}

Moore, P, Iliant, T-M, Ion, F-A, Wu, Y & Lyons, T 2022, Path signatures for non-intrusive load monitoring. in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, New York, N.Y., pp. 3808-3812, 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 22/05/22. https://doi.org/10.1109/ICASSP43922.2022.9747285

Path signatures for non-intrusive load monitoring. / Moore, Paul; Iliant, Theodor-Mihai ; Ion, Filip-Alexandru et al.
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York, N.Y.: IEEE, 2022. p. 3808-3812 (ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Path signatures for non-intrusive load monitoring

AU - Moore, Paul

AU - Iliant, Theodor-Mihai

AU - Ion, Filip-Alexandru

AU - Wu, Yue

AU - Lyons, Terry

N1 - © 2022 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 - 2022/5/27

Y1 - 2022/5/27

N2 - Non-intrusive load monitoring (NILM) is the analysis of electricity loads by means of a single supply wire, so avoiding separate monitors on individual appliances. Some approaches to NILM use the V-I trajectory for feature generation but they apply ad-hoc rules to generate the feature vector. This paper demonstrates a systematic method of feature generation called the path signature which has recently been applied in machine learning, often with notable success. We show how the path signature generates features from the V-I trajectory to give a test set accuracy of 98.81% on the COOLL dataset. We conclude that the path signature is easier to use and generalize than ad-hoc features, and it can be applied to many other applications which use multivariate sequential data.

AB - Non-intrusive load monitoring (NILM) is the analysis of electricity loads by means of a single supply wire, so avoiding separate monitors on individual appliances. Some approaches to NILM use the V-I trajectory for feature generation but they apply ad-hoc rules to generate the feature vector. This paper demonstrates a systematic method of feature generation called the path signature which has recently been applied in machine learning, often with notable success. We show how the path signature generates features from the V-I trajectory to give a test set accuracy of 98.81% on the COOLL dataset. We conclude that the path signature is easier to use and generalize than ad-hoc features, and it can be applied to many other applications which use multivariate sequential data.

KW - non-intrusive load monitoring

KW - disaggregation

KW - machine learning

KW - feature selection

KW - path signatures

U2 - 10.1109/ICASSP43922.2022.9747285

DO - 10.1109/ICASSP43922.2022.9747285

M3 - Conference contribution book

SN - 9781665405416

T3 - ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

SP - 3808

EP - 3812

BT - ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

CY - New York, N.Y.

T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 22 May 2022 through 27 May 2022

ER -

Moore P, Iliant TM, Ion FA, Wu Y, Lyons T. Path signatures for non-intrusive load monitoring. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York, N.Y.: IEEE. 2022. p. 3808-3812. (ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). Epub 2022 Apr 27. doi: 10.1109/ICASSP43922.2022.9747285

Path signatures for non-intrusive load monitoring

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this