A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU
The temporal data of the power system are expanding with the growth of the power system and the proliferation of automated equipment. However, data loss may arise during the acquisition, measurement, transmission, and storage of temporal data. To address the insufficiency of temporal data in the pow...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/7/1590 |
| _version_ | 1797608132852056064 |
|---|---|
| author | Kangmin Xie Jichun Liu Youbo Liu |
| author_facet | Kangmin Xie Jichun Liu Youbo Liu |
| author_sort | Kangmin Xie |
| collection | DOAJ |
| description | The temporal data of the power system are expanding with the growth of the power system and the proliferation of automated equipment. However, data loss may arise during the acquisition, measurement, transmission, and storage of temporal data. To address the insufficiency of temporal data in the power system, this study proposes a sequence-to-sequence (Seq2Seq) architecture to restore power system temporal data. This architecture comprises a radial convolutional neural unit (CNN) network and a gated recurrent unit (GRU) network. Specifically, to account for the periodicity and volatility of temporal data, VMD is employed to decompose the time series data output into components of different frequencies. CNN is utilized to extract the spatial characteristics of temporal data. At the same time, Seq2Seq is employed to reconstruct each component based on introducing a feature timing and multi-model combination triple attention mechanism. The feature attention mechanism calculates the contribution rate of each feature quantity and independently mines the correlation between the time series data output and each feature value. The temporal attention mechanism autonomously extracts historical–critical moment information. A multi-model combination attention mechanism is introduced, and the missing data repair value is obtained after modeling the combination of data on both sides of the missing data. Recovery experiments are conducted based on actual data, and the method’s effectiveness is verified by comparison with other methods. |
| first_indexed | 2024-03-11T05:40:18Z |
| format | Article |
| id | doaj.art-e8d0d72e4f284db5b135caab70261f40 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T05:40:18Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-e8d0d72e4f284db5b135caab70261f402023-11-17T16:32:46ZengMDPI AGElectronics2079-92922023-03-01127159010.3390/electronics12071590A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRUKangmin Xie0Jichun Liu1Youbo Liu2School of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaSchool of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaSchool of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaThe temporal data of the power system are expanding with the growth of the power system and the proliferation of automated equipment. However, data loss may arise during the acquisition, measurement, transmission, and storage of temporal data. To address the insufficiency of temporal data in the power system, this study proposes a sequence-to-sequence (Seq2Seq) architecture to restore power system temporal data. This architecture comprises a radial convolutional neural unit (CNN) network and a gated recurrent unit (GRU) network. Specifically, to account for the periodicity and volatility of temporal data, VMD is employed to decompose the time series data output into components of different frequencies. CNN is utilized to extract the spatial characteristics of temporal data. At the same time, Seq2Seq is employed to reconstruct each component based on introducing a feature timing and multi-model combination triple attention mechanism. The feature attention mechanism calculates the contribution rate of each feature quantity and independently mines the correlation between the time series data output and each feature value. The temporal attention mechanism autonomously extracts historical–critical moment information. A multi-model combination attention mechanism is introduced, and the missing data repair value is obtained after modeling the combination of data on both sides of the missing data. Recovery experiments are conducted based on actual data, and the method’s effectiveness is verified by comparison with other methods.https://www.mdpi.com/2079-9292/12/7/1590neural networksVMDdata reconfigurationattention mechanisms |
| spellingShingle | Kangmin Xie Jichun Liu Youbo Liu A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU Electronics neural networks VMD data reconfiguration attention mechanisms |
| title | A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU |
| title_full | A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU |
| title_fullStr | A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU |
| title_full_unstemmed | A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU |
| title_short | A Power System Timing Data Recovery Method Based on Improved VMD and Attention Mechanism Bi-Directional CNN-GRU |
| title_sort | power system timing data recovery method based on improved vmd and attention mechanism bi directional cnn gru |
| topic | neural networks VMD data reconfiguration attention mechanisms |
| url | https://www.mdpi.com/2079-9292/12/7/1590 |
| work_keys_str_mv | AT kangminxie apowersystemtimingdatarecoverymethodbasedonimprovedvmdandattentionmechanismbidirectionalcnngru AT jichunliu apowersystemtimingdatarecoverymethodbasedonimprovedvmdandattentionmechanismbidirectionalcnngru AT youboliu apowersystemtimingdatarecoverymethodbasedonimprovedvmdandattentionmechanismbidirectionalcnngru AT kangminxie powersystemtimingdatarecoverymethodbasedonimprovedvmdandattentionmechanismbidirectionalcnngru AT jichunliu powersystemtimingdatarecoverymethodbasedonimprovedvmdandattentionmechanismbidirectionalcnngru AT youboliu powersystemtimingdatarecoverymethodbasedonimprovedvmdandattentionmechanismbidirectionalcnngru |