Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems
For a variety of applications within power systems, the precision of data acquisition is of paramount importance. However, the actual data may be corrupted by noise in the process of measurement or transmission, and the accuracy of dynamic security assessment (DSA) will be affected. In light of the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843214/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590356092289024 |
|---|---|
| author | Jian Li Guoqiang Lu Yongbin Li Dongning Zhao Huaiyuan Wang Yucheng Ouyang |
| author_facet | Jian Li Guoqiang Lu Yongbin Li Dongning Zhao Huaiyuan Wang Yucheng Ouyang |
| author_sort | Jian Li |
| collection | DOAJ |
| description | For a variety of applications within power systems, the precision of data acquisition is of paramount importance. However, the actual data may be corrupted by noise in the process of measurement or transmission, and the accuracy of dynamic security assessment (DSA) will be affected. In light of the poor interpretability exhibited by traditional machine learning (ML) methods in denoising, a physics-informed denoising model (PIDM) for dynamic data recovery is proposed. The differential equations of physical models in power systems are employed to guide the training of PIDM. They are transformed into physical constraints and subsequently incorporated into the loss function of stacked denoising autoencoder (SDAE) to cleanse noisy data. By integrating the powerful learning capabilities of ML with the rigorous constraints of physical laws, the noisy data recovered by PIDM can better satisfy the dynamic equations. Consequently, a more pronounced denoising effect can be achieved. The improvement of the PIDM over common ML-based models is explored when dealing with the noisy data with varying degrees of interference or those of unexpected faults. The effectiveness is validated through simulation results in IEEE 39-bus system and the East China power grid. The results show that this method can reduce the total mean square error (MSE) of the recovery of noisy data to at least 65.27% of that of the traditional methods under the same conditions. In addition to demonstrating superior denoising performance, the generalization capability under diverse noise conditions is also deemed excellent. |
| format | Article |
| id | doaj-art-bf7872496bc74cc1940182d22b2aea77 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bf7872496bc74cc1940182d22b2aea772025-01-24T00:01:33ZengIEEEIEEE Access2169-35362025-01-0113120021201310.1109/ACCESS.2025.352985310843214Physics-Informed Denoising Model for Dynamic Data Recovery of Power SystemsJian Li0Guoqiang Lu1Yongbin Li2Dongning Zhao3Huaiyuan Wang4https://orcid.org/0000-0003-4349-826XYucheng Ouyang5State Grid Qinghai Electric Power Company, Xining, ChinaState Grid Qinghai Electric Power Company, Xining, ChinaState Grid Qinghai Electric Power Company, Xining, ChinaState Grid Qinghai Electric Power Company, Xining, ChinaCollege of Electrical Engineering and Automation, Fuzhou University, Fuzhou, ChinaCollege of Electrical Engineering and Automation, Fuzhou University, Fuzhou, ChinaFor a variety of applications within power systems, the precision of data acquisition is of paramount importance. However, the actual data may be corrupted by noise in the process of measurement or transmission, and the accuracy of dynamic security assessment (DSA) will be affected. In light of the poor interpretability exhibited by traditional machine learning (ML) methods in denoising, a physics-informed denoising model (PIDM) for dynamic data recovery is proposed. The differential equations of physical models in power systems are employed to guide the training of PIDM. They are transformed into physical constraints and subsequently incorporated into the loss function of stacked denoising autoencoder (SDAE) to cleanse noisy data. By integrating the powerful learning capabilities of ML with the rigorous constraints of physical laws, the noisy data recovered by PIDM can better satisfy the dynamic equations. Consequently, a more pronounced denoising effect can be achieved. The improvement of the PIDM over common ML-based models is explored when dealing with the noisy data with varying degrees of interference or those of unexpected faults. The effectiveness is validated through simulation results in IEEE 39-bus system and the East China power grid. The results show that this method can reduce the total mean square error (MSE) of the recovery of noisy data to at least 65.27% of that of the traditional methods under the same conditions. In addition to demonstrating superior denoising performance, the generalization capability under diverse noise conditions is also deemed excellent.https://ieeexplore.ieee.org/document/10843214/Data recoverystacked denoising auto-encoderdenoising and physics-informed method |
| spellingShingle | Jian Li Guoqiang Lu Yongbin Li Dongning Zhao Huaiyuan Wang Yucheng Ouyang Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems IEEE Access Data recovery stacked denoising auto-encoder denoising and physics-informed method |
| title | Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems |
| title_full | Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems |
| title_fullStr | Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems |
| title_full_unstemmed | Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems |
| title_short | Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems |
| title_sort | physics informed denoising model for dynamic data recovery of power systems |
| topic | Data recovery stacked denoising auto-encoder denoising and physics-informed method |
| url | https://ieeexplore.ieee.org/document/10843214/ |
| work_keys_str_mv | AT jianli physicsinformeddenoisingmodelfordynamicdatarecoveryofpowersystems AT guoqianglu physicsinformeddenoisingmodelfordynamicdatarecoveryofpowersystems AT yongbinli physicsinformeddenoisingmodelfordynamicdatarecoveryofpowersystems AT dongningzhao physicsinformeddenoisingmodelfordynamicdatarecoveryofpowersystems AT huaiyuanwang physicsinformeddenoisingmodelfordynamicdatarecoveryofpowersystems AT yuchengouyang physicsinformeddenoisingmodelfordynamicdatarecoveryofpowersystems |