Non-intrusive appliance load monitoring using low-resolution smart meter data

Research output: Contribution to conferencePaper

37 Citations (Scopus)

Abstract

We propose two algorithms for power load disaggregation at low-sampling rates (greater than 1sec): a low-complexity, supervised approach based on Decision Trees and an unsupervised method based on Dynamic Time Warping. Both proposed algorithms share common pre-classification steps. We provide reproducible algorithmic description and benchmark the proposed methods with a state-of-the-art Hidden Markov Model (HMM)-based approach. Experimental results using three US and three UK households, show that both proposed methods outperform the HMM-based approach and are capable of disaggregating a range of domestic loads even when the training period is very short.

Conference

ConferenceIEEE International Conference on Smart Grid Communications
CountryItaly
CityVenice
Period3/11/146/11/14
Internet address

Fingerprint

Smart meters
Hidden Markov models
Monitoring
Decision trees
Sampling

Keywords

  • decision trees
  • domestic appliances
  • hidden Markov models
  • load management
  • smart meters

Cite this

Liao, J., Elafoudi, G., Stankovic, L., & Stankovic, V. (2014). Non-intrusive appliance load monitoring using low-resolution smart meter data. 535-540. Paper presented at IEEE International Conference on Smart Grid Communications, Venice, Italy. https://doi.org/10.1109/SmartGridComm.2014.7007702
Liao, Jing ; Elafoudi, G. ; Stankovic, L. ; Stankovic, V. / Non-intrusive appliance load monitoring using low-resolution smart meter data. Paper presented at IEEE International Conference on Smart Grid Communications, Venice, Italy.6 p.
@conference{4d04d8542cf046d8a25c4b5b9e6cc41b,
title = "Non-intrusive appliance load monitoring using low-resolution smart meter data",
abstract = "We propose two algorithms for power load disaggregation at low-sampling rates (greater than 1sec): a low-complexity, supervised approach based on Decision Trees and an unsupervised method based on Dynamic Time Warping. Both proposed algorithms share common pre-classification steps. We provide reproducible algorithmic description and benchmark the proposed methods with a state-of-the-art Hidden Markov Model (HMM)-based approach. Experimental results using three US and three UK households, show that both proposed methods outperform the HMM-based approach and are capable of disaggregating a range of domestic loads even when the training period is very short.",
keywords = "decision trees, domestic appliances, hidden Markov models, load management, smart meters",
author = "Jing Liao and G. Elafoudi and L. Stankovic and V. Stankovic",
year = "2014",
month = "11",
doi = "10.1109/SmartGridComm.2014.7007702",
language = "English",
pages = "535--540",
note = "IEEE International Conference on Smart Grid Communications ; Conference date: 03-11-2014 Through 06-11-2014",
url = "http://sgc2014.ieee-smartgridcomm.org/",

}

Liao, J, Elafoudi, G, Stankovic, L & Stankovic, V 2014, 'Non-intrusive appliance load monitoring using low-resolution smart meter data' Paper presented at IEEE International Conference on Smart Grid Communications, Venice, Italy, 3/11/14 - 6/11/14, pp. 535-540. https://doi.org/10.1109/SmartGridComm.2014.7007702

Non-intrusive appliance load monitoring using low-resolution smart meter data. / Liao, Jing; Elafoudi, G.; Stankovic, L.; Stankovic, V.

2014. 535-540 Paper presented at IEEE International Conference on Smart Grid Communications, Venice, Italy.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Non-intrusive appliance load monitoring using low-resolution smart meter data

AU - Liao, Jing

AU - Elafoudi, G.

AU - Stankovic, L.

AU - Stankovic, V.

PY - 2014/11

Y1 - 2014/11

N2 - We propose two algorithms for power load disaggregation at low-sampling rates (greater than 1sec): a low-complexity, supervised approach based on Decision Trees and an unsupervised method based on Dynamic Time Warping. Both proposed algorithms share common pre-classification steps. We provide reproducible algorithmic description and benchmark the proposed methods with a state-of-the-art Hidden Markov Model (HMM)-based approach. Experimental results using three US and three UK households, show that both proposed methods outperform the HMM-based approach and are capable of disaggregating a range of domestic loads even when the training period is very short.

AB - We propose two algorithms for power load disaggregation at low-sampling rates (greater than 1sec): a low-complexity, supervised approach based on Decision Trees and an unsupervised method based on Dynamic Time Warping. Both proposed algorithms share common pre-classification steps. We provide reproducible algorithmic description and benchmark the proposed methods with a state-of-the-art Hidden Markov Model (HMM)-based approach. Experimental results using three US and three UK households, show that both proposed methods outperform the HMM-based approach and are capable of disaggregating a range of domestic loads even when the training period is very short.

KW - decision trees

KW - domestic appliances

KW - hidden Markov models

KW - load management

KW - smart meters

UR - http://sgc2014.ieee-smartgridcomm.org/

U2 - 10.1109/SmartGridComm.2014.7007702

DO - 10.1109/SmartGridComm.2014.7007702

M3 - Paper

SP - 535

EP - 540

ER -

Liao J, Elafoudi G, Stankovic L, Stankovic V. Non-intrusive appliance load monitoring using low-resolution smart meter data. 2014. Paper presented at IEEE International Conference on Smart Grid Communications, Venice, Italy. https://doi.org/10.1109/SmartGridComm.2014.7007702