Cargando…

Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism

A critical issue in intelligent building control is detecting energy consumption anomalies based on intelligent device status data. The building field is plagued by energy consumption anomalies caused by a number of factors, many of which are associated with one another in apparent temporal relation...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Zhe, Chen, Yuhao, Wang, Huixue, Fu, Qiming, Chen, Jianping, Lu, You
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10249861/
https://www.ncbi.nlm.nih.gov/pubmed/37289704
http://dx.doi.org/10.1371/journal.pone.0286770
_version_ 1785055634980339712
author Zhang, Zhe
Chen, Yuhao
Wang, Huixue
Fu, Qiming
Chen, Jianping
Lu, You
author_facet Zhang, Zhe
Chen, Yuhao
Wang, Huixue
Fu, Qiming
Chen, Jianping
Lu, You
author_sort Zhang, Zhe
collection PubMed
description A critical issue in intelligent building control is detecting energy consumption anomalies based on intelligent device status data. The building field is plagued by energy consumption anomalies caused by a number of factors, many of which are associated with one another in apparent temporal relationships. For the detection of abnormalities, most traditional detection methods rely solely on a single variable of energy consumption data and its time series changes. Therefore, they are unable to examine the correlation between the multiple characteristic factors that affect energy consumption anomalies and their relationship in time. The outcomes of anomaly detection are one-sided. To address the above problems, this paper proposes an anomaly detection method based on multivariate time series. Firstly, in order to extract the correlation between different feature variables affecting energy consumption, this paper introduces a graph convolutional network to build an anomaly detection framework. Secondly, as different feature variables have different influences on each other, the framework is enhanced by a graph attention mechanism so that time series features with higher influence on energy consumption are given more attention weights, resulting in better anomaly detection of building energy consumption. Finally, the effectiveness of this paper’s method and existing methods for detecting energy consumption anomalies in smart buildings are compared using standard data sets. The experimental results show that the model has better detection accuracy.
format Online
Article
Text
id pubmed-10249861
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-102498612023-06-09 Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism Zhang, Zhe Chen, Yuhao Wang, Huixue Fu, Qiming Chen, Jianping Lu, You PLoS One Research Article A critical issue in intelligent building control is detecting energy consumption anomalies based on intelligent device status data. The building field is plagued by energy consumption anomalies caused by a number of factors, many of which are associated with one another in apparent temporal relationships. For the detection of abnormalities, most traditional detection methods rely solely on a single variable of energy consumption data and its time series changes. Therefore, they are unable to examine the correlation between the multiple characteristic factors that affect energy consumption anomalies and their relationship in time. The outcomes of anomaly detection are one-sided. To address the above problems, this paper proposes an anomaly detection method based on multivariate time series. Firstly, in order to extract the correlation between different feature variables affecting energy consumption, this paper introduces a graph convolutional network to build an anomaly detection framework. Secondly, as different feature variables have different influences on each other, the framework is enhanced by a graph attention mechanism so that time series features with higher influence on energy consumption are given more attention weights, resulting in better anomaly detection of building energy consumption. Finally, the effectiveness of this paper’s method and existing methods for detecting energy consumption anomalies in smart buildings are compared using standard data sets. The experimental results show that the model has better detection accuracy. Public Library of Science 2023-06-08 /pmc/articles/PMC10249861/ /pubmed/37289704 http://dx.doi.org/10.1371/journal.pone.0286770 Text en © 2023 Zhang et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Zhang, Zhe
Chen, Yuhao
Wang, Huixue
Fu, Qiming
Chen, Jianping
Lu, You
Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
title Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
title_full Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
title_fullStr Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
title_full_unstemmed Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
title_short Anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
title_sort anomaly detection method for building energy consumption in multivariate time series based on graph attention mechanism
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10249861/
https://www.ncbi.nlm.nih.gov/pubmed/37289704
http://dx.doi.org/10.1371/journal.pone.0286770
work_keys_str_mv AT zhangzhe anomalydetectionmethodforbuildingenergyconsumptioninmultivariatetimeseriesbasedongraphattentionmechanism
AT chenyuhao anomalydetectionmethodforbuildingenergyconsumptioninmultivariatetimeseriesbasedongraphattentionmechanism
AT wanghuixue anomalydetectionmethodforbuildingenergyconsumptioninmultivariatetimeseriesbasedongraphattentionmechanism
AT fuqiming anomalydetectionmethodforbuildingenergyconsumptioninmultivariatetimeseriesbasedongraphattentionmechanism
AT chenjianping anomalydetectionmethodforbuildingenergyconsumptioninmultivariatetimeseriesbasedongraphattentionmechanism
AT luyou anomalydetectionmethodforbuildingenergyconsumptioninmultivariatetimeseriesbasedongraphattentionmechanism