ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring
Non-Intrusive Load Monitoring (NILM) describes the process of inferring the consumption pattern of appliances by only having access to the aggregated household signal. Sequence-to-sequence deep learning models have been firmly established as state-of-the-art approaches for NILM, in an attempt to ide...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/8/2926 |
_version_ | 1797443795088834560 |
---|---|
author | Stavros Sykiotis Maria Kaselimi Anastasios Doulamis Nikolaos Doulamis |
author_facet | Stavros Sykiotis Maria Kaselimi Anastasios Doulamis Nikolaos Doulamis |
author_sort | Stavros Sykiotis |
collection | DOAJ |
description | Non-Intrusive Load Monitoring (NILM) describes the process of inferring the consumption pattern of appliances by only having access to the aggregated household signal. Sequence-to-sequence deep learning models have been firmly established as state-of-the-art approaches for NILM, in an attempt to identify the pattern of the appliance power consumption signal into the aggregated power signal. Exceeding the limitations of recurrent models that have been widely used in sequential modeling, this paper proposes a transformer-based architecture for NILM. Our approach, called ELECTRIcity, utilizes transformer layers to accurately estimate the power signal of domestic appliances by relying entirely on attention mechanisms to extract global dependencies between the aggregate and the domestic appliance signals. Another additive value of the proposed model is that ELECTRIcity works with minimal dataset pre-processing and without requiring data balancing. Furthermore, ELECTRIcity introduces an efficient training routine compared to other traditional transformer-based architectures. According to this routine, ELECTRIcity splits model training into unsupervised pre-training and downstream task fine-tuning, which yields performance increases in both predictive accuracy and training time decrease. Experimental results indicate ELECTRIcity’s superiority compared to several state-of-the-art methods. |
first_indexed | 2024-03-09T13:03:10Z |
format | Article |
id | doaj.art-cbbfea0f3faf48f0b604e84e54cf7913 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T13:03:10Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-cbbfea0f3faf48f0b604e84e54cf79132023-11-30T21:52:42ZengMDPI AGSensors1424-82202022-04-01228292610.3390/s22082926ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringStavros Sykiotis0Maria Kaselimi1Anastasios Doulamis2Nikolaos Doulamis3School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceSchool of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceSchool of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceSchool of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceNon-Intrusive Load Monitoring (NILM) describes the process of inferring the consumption pattern of appliances by only having access to the aggregated household signal. Sequence-to-sequence deep learning models have been firmly established as state-of-the-art approaches for NILM, in an attempt to identify the pattern of the appliance power consumption signal into the aggregated power signal. Exceeding the limitations of recurrent models that have been widely used in sequential modeling, this paper proposes a transformer-based architecture for NILM. Our approach, called ELECTRIcity, utilizes transformer layers to accurately estimate the power signal of domestic appliances by relying entirely on attention mechanisms to extract global dependencies between the aggregate and the domestic appliance signals. Another additive value of the proposed model is that ELECTRIcity works with minimal dataset pre-processing and without requiring data balancing. Furthermore, ELECTRIcity introduces an efficient training routine compared to other traditional transformer-based architectures. According to this routine, ELECTRIcity splits model training into unsupervised pre-training and downstream task fine-tuning, which yields performance increases in both predictive accuracy and training time decrease. Experimental results indicate ELECTRIcity’s superiority compared to several state-of-the-art methods.https://www.mdpi.com/1424-8220/22/8/2926NILMnon-intrusive load monitoringtransformersenergy disaggregationimbalanced datadeep learning |
spellingShingle | Stavros Sykiotis Maria Kaselimi Anastasios Doulamis Nikolaos Doulamis ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring Sensors NILM non-intrusive load monitoring transformers energy disaggregation imbalanced data deep learning |
title | ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring |
title_full | ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring |
title_fullStr | ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring |
title_full_unstemmed | ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring |
title_short | ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring |
title_sort | electricity an efficient transformer for non intrusive load monitoring |
topic | NILM non-intrusive load monitoring transformers energy disaggregation imbalanced data deep learning |
url | https://www.mdpi.com/1424-8220/22/8/2926 |
work_keys_str_mv | AT stavrossykiotis electricityanefficienttransformerfornonintrusiveloadmonitoring AT mariakaselimi electricityanefficienttransformerfornonintrusiveloadmonitoring AT anastasiosdoulamis electricityanefficienttransformerfornonintrusiveloadmonitoring AT nikolaosdoulamis electricityanefficienttransformerfornonintrusiveloadmonitoring |