A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System
Maintaining transient stability is a core requirement for ensuring safe operation of power systems. Hence, quick and accurate assessment of the transient stability of power systems is particularly critical. As the deployment of wide area measurement systems (WAMS) expands, transient stability assess...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8740932/ |
| _version_ | 1818922179163586560 |
|---|---|
| author | Bendong Tan Jun Yang Yufei Tang Shengbo Jiang Peiyuan Xie Wen Yuan |
| author_facet | Bendong Tan Jun Yang Yufei Tang Shengbo Jiang Peiyuan Xie Wen Yuan |
| author_sort | Bendong Tan |
| collection | DOAJ |
| description | Maintaining transient stability is a core requirement for ensuring safe operation of power systems. Hence, quick and accurate assessment of the transient stability of power systems is particularly critical. As the deployment of wide area measurement systems (WAMS) expands, transient stability assessment (TSA) based on machine learning with data of phasors measurement units (PMUs) also develops rapidly. However, unstable samples of the power system are rarely seen in practice which affects greatly the effectiveness of transient instability recognition. To address this problem, we propose a deep imbalanced learning-based TSA framework. First, an improved denoising autoencoder (DAE) is constructed to map the training set to hidden space for dimension reduction. Then, adaptive synthetic sampling (ADASYN) is further used to synthesize unstable samples in hidden space to balance the proportion of different classes. Third, the synthesized data are decoded into the original space to enhance the training set. Finally, an ensemble cost-sensitive classifier based on a stacked denoising autoencoder (SDAE) is designed to extract different feature patterns, and the SDAEs are merged with a fusion layer to classify the status of the power system. The simulation results of two benchmark power systems indicate that the proposed method can effectively improve the recognition accuracy of unstable cases by combining nonlinear data synthesis with ensemble cost-sensitive learning methods. Compared with other imbalanced learning methods, the proposed framework enjoys superiority both in accuracy and G-mean. |
| first_indexed | 2024-12-20T01:49:25Z |
| format | Article |
| id | doaj.art-d5c26bb442104bc69becb9cec6dbf2fe |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T01:49:25Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d5c26bb442104bc69becb9cec6dbf2fe2022-12-21T19:57:41ZengIEEEIEEE Access2169-35362019-01-017817598176910.1109/ACCESS.2019.29237998740932A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power SystemBendong Tan0https://orcid.org/0000-0003-1701-1577Jun Yang1Yufei Tang2Shengbo Jiang3Peiyuan Xie4Wen Yuan5School of Electrical Engineering and Automation, Wuhan University, Wuhan, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan, ChinaDepartment of Computer and Electrical Engineering and Computer Science, Institute for Sensing and Embedded Network Systems Engineering, Florida Atlantic University, Boca Raton, FL, USASchool of Electrical Engineering and Automation, Wuhan University, Wuhan, ChinaState Grid Hunan Electric Power Company Ltd., Changsha, ChinaState Grid Hunan Electric Power Company Ltd., Changsha, ChinaMaintaining transient stability is a core requirement for ensuring safe operation of power systems. Hence, quick and accurate assessment of the transient stability of power systems is particularly critical. As the deployment of wide area measurement systems (WAMS) expands, transient stability assessment (TSA) based on machine learning with data of phasors measurement units (PMUs) also develops rapidly. However, unstable samples of the power system are rarely seen in practice which affects greatly the effectiveness of transient instability recognition. To address this problem, we propose a deep imbalanced learning-based TSA framework. First, an improved denoising autoencoder (DAE) is constructed to map the training set to hidden space for dimension reduction. Then, adaptive synthetic sampling (ADASYN) is further used to synthesize unstable samples in hidden space to balance the proportion of different classes. Third, the synthesized data are decoded into the original space to enhance the training set. Finally, an ensemble cost-sensitive classifier based on a stacked denoising autoencoder (SDAE) is designed to extract different feature patterns, and the SDAEs are merged with a fusion layer to classify the status of the power system. The simulation results of two benchmark power systems indicate that the proposed method can effectively improve the recognition accuracy of unstable cases by combining nonlinear data synthesis with ensemble cost-sensitive learning methods. Compared with other imbalanced learning methods, the proposed framework enjoys superiority both in accuracy and G-mean.https://ieeexplore.ieee.org/document/8740932/Deep imbalanced learningtransient stability of power systemdenoising autoencoder (DAE)ensemble cost-sensitive SDAEfeature patternsG-mean |
| spellingShingle | Bendong Tan Jun Yang Yufei Tang Shengbo Jiang Peiyuan Xie Wen Yuan A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System IEEE Access Deep imbalanced learning transient stability of power system denoising autoencoder (DAE) ensemble cost-sensitive SDAE feature patterns G-mean |
| title | A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System |
| title_full | A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System |
| title_fullStr | A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System |
| title_full_unstemmed | A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System |
| title_short | A Deep Imbalanced Learning Framework for Transient Stability Assessment of Power System |
| title_sort | deep imbalanced learning framework for transient stability assessment of power system |
| topic | Deep imbalanced learning transient stability of power system denoising autoencoder (DAE) ensemble cost-sensitive SDAE feature patterns G-mean |
| url | https://ieeexplore.ieee.org/document/8740932/ |
| work_keys_str_mv | AT bendongtan adeepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT junyang adeepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT yufeitang adeepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT shengbojiang adeepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT peiyuanxie adeepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT wenyuan adeepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT bendongtan deepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT junyang deepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT yufeitang deepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT shengbojiang deepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT peiyuanxie deepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem AT wenyuan deepimbalancedlearningframeworkfortransientstabilityassessmentofpowersystem |