A electricity theft detection method through contrastive learning in smart grid
Abstract As an important edge device of power grid, smart meters enable the detection of illegal behaviors such as electricity theft by analyzing large-scale electricity consumption data. Electricity theft poses a major threat to the economy and the security of society. Electricity theft detection (...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-06-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13638-023-02258-z |
| _version_ | 1797795900030976000 |
|---|---|
| author | Zijian Liu Weilong Ding Tao Chen Maoxiang Sun Hongmin Cai Chen Liu |
| author_facet | Zijian Liu Weilong Ding Tao Chen Maoxiang Sun Hongmin Cai Chen Liu |
| author_sort | Zijian Liu |
| collection | DOAJ |
| description | Abstract As an important edge device of power grid, smart meters enable the detection of illegal behaviors such as electricity theft by analyzing large-scale electricity consumption data. Electricity theft poses a major threat to the economy and the security of society. Electricity theft detection (ETD) methods can effectively reduce losses and suppress illegal behaviors. On electricity consumption data from smart meters, ETD methods always train deep learning models. However, these methods are limited to extract different electricity consumption characteristics between independent users, and the pattern differences between users cannot be actively learned. Such difficulty prevents ETD further performance improvement. Therefore, a novel ETD method is proposed, which is the first attempt to apply supervised contrastive learning for electricity theft detection. On the one hand, our method allows the detection model to improve its detection performance by actively comparing users’ representation vectors. On the other hand, in order to obtain high-quality augmented views, largest triangle three buckets time series downsampling is adopted innovatively to improve model stability through data augment. Experiments on real-world datasets show that our model outperforms state-of-the-art models. |
| first_indexed | 2024-03-13T03:24:59Z |
| format | Article |
| id | doaj.art-2db2852e622e4fa9b3b58be9245c4cf6 |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-03-13T03:24:59Z |
| publishDate | 2023-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-2db2852e622e4fa9b3b58be9245c4cf62023-06-25T11:03:52ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992023-06-012023111710.1186/s13638-023-02258-zA electricity theft detection method through contrastive learning in smart gridZijian Liu0Weilong Ding1Tao Chen2Maoxiang Sun3Hongmin Cai4Chen Liu5School of Information Science and Technology, North China University of TechnologySchool of Information Science and Technology, North China University of TechnologyBeijing China-Power Information Technology Co.,LtdSchool of Information Science and Technology, North China University of TechnologySchool of Computer Science and Engineering, South China University of TechnologySchool of Information Science and Technology, North China University of TechnologyAbstract As an important edge device of power grid, smart meters enable the detection of illegal behaviors such as electricity theft by analyzing large-scale electricity consumption data. Electricity theft poses a major threat to the economy and the security of society. Electricity theft detection (ETD) methods can effectively reduce losses and suppress illegal behaviors. On electricity consumption data from smart meters, ETD methods always train deep learning models. However, these methods are limited to extract different electricity consumption characteristics between independent users, and the pattern differences between users cannot be actively learned. Such difficulty prevents ETD further performance improvement. Therefore, a novel ETD method is proposed, which is the first attempt to apply supervised contrastive learning for electricity theft detection. On the one hand, our method allows the detection model to improve its detection performance by actively comparing users’ representation vectors. On the other hand, in order to obtain high-quality augmented views, largest triangle three buckets time series downsampling is adopted innovatively to improve model stability through data augment. Experiments on real-world datasets show that our model outperforms state-of-the-art models.https://doi.org/10.1186/s13638-023-02258-zSmart gridElectricity theft detectionContrastive learning |
| spellingShingle | Zijian Liu Weilong Ding Tao Chen Maoxiang Sun Hongmin Cai Chen Liu A electricity theft detection method through contrastive learning in smart grid EURASIP Journal on Wireless Communications and Networking Smart grid Electricity theft detection Contrastive learning |
| title | A electricity theft detection method through contrastive learning in smart grid |
| title_full | A electricity theft detection method through contrastive learning in smart grid |
| title_fullStr | A electricity theft detection method through contrastive learning in smart grid |
| title_full_unstemmed | A electricity theft detection method through contrastive learning in smart grid |
| title_short | A electricity theft detection method through contrastive learning in smart grid |
| title_sort | electricity theft detection method through contrastive learning in smart grid |
| topic | Smart grid Electricity theft detection Contrastive learning |
| url | https://doi.org/10.1186/s13638-023-02258-z |
| work_keys_str_mv | AT zijianliu aelectricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT weilongding aelectricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT taochen aelectricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT maoxiangsun aelectricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT hongmincai aelectricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT chenliu aelectricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT zijianliu electricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT weilongding electricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT taochen electricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT maoxiangsun electricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT hongmincai electricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid AT chenliu electricitytheftdetectionmethodthroughcontrastivelearninginsmartgrid |