Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification
A two-stage machine learning-based approach for creating synthetic phasor measurement unit (PMU) data is proposed in this article. This approach leverages generative adversarial networks (GAN) in data generation and incorporates neural ordinary differential equation (Neural ODE) to guarantee underly...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Open Access Journal of Power and Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9361704/ |
| id |
doaj-7ada7b7c68414c69843cd339085bcd93 |
|---|---|
| record_format |
Article |
| spelling |
doaj-7ada7b7c68414c69843cd339085bcd932021-03-30T15:05:37ZengIEEEIEEE Open Access Journal of Power and Energy2687-79102021-01-018687610.1109/OAJPE.2021.30616489361704Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event ClassificationXiangtian Zheng0https://orcid.org/0000-0003-2884-3213Bin Wang1https://orcid.org/0000-0003-4199-4403Dileep Kalathil2https://orcid.org/0000-0001-7968-5185Le Xie3https://orcid.org/0000-0002-9810-948XDepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USADepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USADepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USADepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USAA two-stage machine learning-based approach for creating synthetic phasor measurement unit (PMU) data is proposed in this article. This approach leverages generative adversarial networks (GAN) in data generation and incorporates neural ordinary differential equation (Neural ODE) to guarantee underlying physical meaning. We utilize this approach to synthetically create massive eventful PMU data, which would otherwise be difficult to obtain from the real world due to the critical energy infrastructure information (CEII) protection. To illustrate the utility of such synthetic data for subsequent data-driven methods, we specifically demonstrate the application of using synthetic PMU data for event classification by scaling up the real data set. The addition of the synthetic PMU data to a small set of real PMU data is shown to have improved the event classification accuracy by 2 to 5 percent.https://ieeexplore.ieee.org/document/9361704/Event classificationphasor measurement unitgenerative adversarial networkneural ODE |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Xiangtian Zheng Bin Wang Dileep Kalathil Le Xie |
| spellingShingle |
Xiangtian Zheng Bin Wang Dileep Kalathil Le Xie Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification IEEE Open Access Journal of Power and Energy Event classification phasor measurement unit generative adversarial network neural ODE |
| author_facet |
Xiangtian Zheng Bin Wang Dileep Kalathil Le Xie |
| author_sort |
Xiangtian Zheng |
| title |
Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification |
| title_short |
Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification |
| title_full |
Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification |
| title_fullStr |
Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification |
| title_full_unstemmed |
Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification |
| title_sort |
generative adversarial networks-based synthetic pmu data creation for improved event classification |
| publisher |
IEEE |
| series |
IEEE Open Access Journal of Power and Energy |
| issn |
2687-7910 |
| publishDate |
2021-01-01 |
| description |
A two-stage machine learning-based approach for creating synthetic phasor measurement unit (PMU) data is proposed in this article. This approach leverages generative adversarial networks (GAN) in data generation and incorporates neural ordinary differential equation (Neural ODE) to guarantee underlying physical meaning. We utilize this approach to synthetically create massive eventful PMU data, which would otherwise be difficult to obtain from the real world due to the critical energy infrastructure information (CEII) protection. To illustrate the utility of such synthetic data for subsequent data-driven methods, we specifically demonstrate the application of using synthetic PMU data for event classification by scaling up the real data set. The addition of the synthetic PMU data to a small set of real PMU data is shown to have improved the event classification accuracy by 2 to 5 percent. |
| topic |
Event classification phasor measurement unit generative adversarial network neural ODE |
| url |
https://ieeexplore.ieee.org/document/9361704/ |
| work_keys_str_mv |
AT xiangtianzheng generativeadversarialnetworksbasedsyntheticpmudatacreationforimprovedeventclassification AT binwang generativeadversarialnetworksbasedsyntheticpmudatacreationforimprovedeventclassification AT dileepkalathil generativeadversarialnetworksbasedsyntheticpmudatacreationforimprovedeventclassification AT lexie generativeadversarialnetworksbasedsyntheticpmudatacreationforimprovedeventclassification |
| _version_ |
1724180109847429120 |