Cargando…
Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation
Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series sm...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7699329/ https://www.ncbi.nlm.nih.gov/pubmed/33228064 http://dx.doi.org/10.3390/s20226628 |
_version_ | 1783616023980670976 |
---|---|
author | He, Kanghang Stankovic, Vladimir Stankovic, Lina |
author_facet | He, Kanghang Stankovic, Vladimir Stankovic, Lina |
author_sort | He, Kanghang |
collection | PubMed |
description | Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series smart meter measurements. We propose a variable-length data segmentation approach to extract potential events, assign all measurements associated with an identified event to each graph node, employ dynamic time warping to define the adjacency matrix of the graph, and propose a robust cluster labeling approach. Our simulation results on four different datasets show up to 10% improvement in classification performance over competing approaches. |
format | Online Article Text |
id | pubmed-7699329 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-76993292020-11-29 Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation He, Kanghang Stankovic, Vladimir Stankovic, Lina Sensors (Basel) Article Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series smart meter measurements. We propose a variable-length data segmentation approach to extract potential events, assign all measurements associated with an identified event to each graph node, employ dynamic time warping to define the adjacency matrix of the graph, and propose a robust cluster labeling approach. Our simulation results on four different datasets show up to 10% improvement in classification performance over competing approaches. MDPI 2020-11-19 /pmc/articles/PMC7699329/ /pubmed/33228064 http://dx.doi.org/10.3390/s20226628 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article He, Kanghang Stankovic, Vladimir Stankovic, Lina Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation |
title | Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation |
title_full | Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation |
title_fullStr | Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation |
title_full_unstemmed | Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation |
title_short | Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation |
title_sort | building a graph signal processing model using dynamic time warping for load disaggregation |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7699329/ https://www.ncbi.nlm.nih.gov/pubmed/33228064 http://dx.doi.org/10.3390/s20226628 |
work_keys_str_mv | AT hekanghang buildingagraphsignalprocessingmodelusingdynamictimewarpingforloaddisaggregation AT stankovicvladimir buildingagraphsignalprocessingmodelusingdynamictimewarpingforloaddisaggregation AT stankoviclina buildingagraphsignalprocessingmodelusingdynamictimewarpingforloaddisaggregation |