Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN
Non-intrusive load monitoring (NILM) is the practice of estimating power consumption of a single household appliance using data from a total power meter of the user’s house. The transformer model has emerged as a popular method for handling NILM problems. However, with the increase in data from elec...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/13/2824 |
_version_ | 1797591822202044416 |
---|---|
author | Zhoupeng Zai Sheng Zhao Zhengjiang Zhang Haolei Li Nianqi Sun |
author_facet | Zhoupeng Zai Sheng Zhao Zhengjiang Zhang Haolei Li Nianqi Sun |
author_sort | Zhoupeng Zai |
collection | DOAJ |
description | Non-intrusive load monitoring (NILM) is the practice of estimating power consumption of a single household appliance using data from a total power meter of the user’s house. The transformer model has emerged as a popular method for handling NILM problems. However, with the increase in data from electricity meters, there is a need for research focusing on the accuracy and computational complexity of the transformer model. To address this, this paper proposes a sequence-to-sequence load decomposition structure named GTCN, which combines the gate-transformer and convolutional neural networks (CNNs). GTCN introduces a gating mechanism to reduce the number of parameters for training the model while maintaining performance. The introduction of CNNs can effectively capture local features that the gate-transformer may not be able to capture, thereby improving the accuracy of power estimation of individual household appliances. The results of the experiments, based on the UK-DALE dataset, illustrate that GTCN not only demonstrates excellent decomposition performance but also reduces the model parameters compared to conventional transformers. Moreover, the proposed GTCN structure, despite maintaining the same number of model parameters as the traditional transformer architecture after incorporating CNNs, outperforms the conventional transformer model, as well as current seq2seq and R-LSTM technologies, and achieves enhanced prediction accuracy and improved generalization capability. |
first_indexed | 2024-03-11T01:43:52Z |
format | Article |
id | doaj.art-427a57f986da4cabbe1fd1bd8ee7fedd |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T01:43:52Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-427a57f986da4cabbe1fd1bd8ee7fedd2023-11-18T16:23:58ZengMDPI AGElectronics2079-92922023-06-011213282410.3390/electronics12132824Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNNZhoupeng Zai0Sheng Zhao1Zhengjiang Zhang2Haolei Li3Nianqi Sun4School of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, ChinaSchool of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, ChinaSchool of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, ChinaSchool of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, ChinaSchool of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, ChinaNon-intrusive load monitoring (NILM) is the practice of estimating power consumption of a single household appliance using data from a total power meter of the user’s house. The transformer model has emerged as a popular method for handling NILM problems. However, with the increase in data from electricity meters, there is a need for research focusing on the accuracy and computational complexity of the transformer model. To address this, this paper proposes a sequence-to-sequence load decomposition structure named GTCN, which combines the gate-transformer and convolutional neural networks (CNNs). GTCN introduces a gating mechanism to reduce the number of parameters for training the model while maintaining performance. The introduction of CNNs can effectively capture local features that the gate-transformer may not be able to capture, thereby improving the accuracy of power estimation of individual household appliances. The results of the experiments, based on the UK-DALE dataset, illustrate that GTCN not only demonstrates excellent decomposition performance but also reduces the model parameters compared to conventional transformers. Moreover, the proposed GTCN structure, despite maintaining the same number of model parameters as the traditional transformer architecture after incorporating CNNs, outperforms the conventional transformer model, as well as current seq2seq and R-LSTM technologies, and achieves enhanced prediction accuracy and improved generalization capability.https://www.mdpi.com/2079-9292/12/13/2824non-intrusive load monitoringgate-transformergating mechanismconvolutional neural networkgeneralization ability |
spellingShingle | Zhoupeng Zai Sheng Zhao Zhengjiang Zhang Haolei Li Nianqi Sun Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN Electronics non-intrusive load monitoring gate-transformer gating mechanism convolutional neural network generalization ability |
title | Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN |
title_full | Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN |
title_fullStr | Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN |
title_full_unstemmed | Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN |
title_short | Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN |
title_sort | non intrusive load monitoring based on the combination of gate transformer and cnn |
topic | non-intrusive load monitoring gate-transformer gating mechanism convolutional neural network generalization ability |
url | https://www.mdpi.com/2079-9292/12/13/2824 |
work_keys_str_mv | AT zhoupengzai nonintrusiveloadmonitoringbasedonthecombinationofgatetransformerandcnn AT shengzhao nonintrusiveloadmonitoringbasedonthecombinationofgatetransformerandcnn AT zhengjiangzhang nonintrusiveloadmonitoringbasedonthecombinationofgatetransformerandcnn AT haoleili nonintrusiveloadmonitoringbasedonthecombinationofgatetransformerandcnn AT nianqisun nonintrusiveloadmonitoringbasedonthecombinationofgatetransformerandcnn |