Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.09936 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911312459595776 |
|---|---|
| author | Li, Yang Ma, Chong Li, Yuanzheng Li, Sen Chen, Yanbo Dong, Zhaoyang |
| author_facet | Li, Yang Ma, Chong Li, Yuanzheng Li, Sen Chen, Yanbo Dong, Zhaoyang |
| contents | Short-term voltage stability assessment (STVSA) is critical for secure power system operation. While classical machine learning-based methods have demonstrated strong performance, they still face challenges in robustness under adversarial conditions. This paper proposes QSTAformer-a tailored quantum-enhanced Transformer architecture that embeds parameterized quantum circuits (PQCs) into attention mechanisms-for robust and efficient STVSA. A dedicated adversarial training strategy is developed to defend against both white-box and gray-box attacks. Furthermore, diverse PQC architectures are benchmarked to explore trade-offs between expressiveness, convergence, and efficiency. To the best of our knowledge, this is the first work to systematically investigate the adversarial vulnerability of quantum machine learning-based STVSA. Case studies on the IEEE 39-bus system demonstrate that QSTAformer achieves competitive accuracy, reduced complexity, and stronger robustness, underscoring its potential for secure and scalable STVSA under adversarial conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09936 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QSTAformer: A Quantum-Enhanced Transformer for Robust Short-Term Voltage Stability Assessment against Adversarial Attacks Li, Yang Ma, Chong Li, Yuanzheng Li, Sen Chen, Yanbo Dong, Zhaoyang Systems and Control Machine Learning Quantum Physics Short-term voltage stability assessment (STVSA) is critical for secure power system operation. While classical machine learning-based methods have demonstrated strong performance, they still face challenges in robustness under adversarial conditions. This paper proposes QSTAformer-a tailored quantum-enhanced Transformer architecture that embeds parameterized quantum circuits (PQCs) into attention mechanisms-for robust and efficient STVSA. A dedicated adversarial training strategy is developed to defend against both white-box and gray-box attacks. Furthermore, diverse PQC architectures are benchmarked to explore trade-offs between expressiveness, convergence, and efficiency. To the best of our knowledge, this is the first work to systematically investigate the adversarial vulnerability of quantum machine learning-based STVSA. Case studies on the IEEE 39-bus system demonstrate that QSTAformer achieves competitive accuracy, reduced complexity, and stronger robustness, underscoring its potential for secure and scalable STVSA under adversarial conditions. |
| title | QSTAformer: A Quantum-Enhanced Transformer for Robust Short-Term Voltage Stability Assessment against Adversarial Attacks |
| topic | Systems and Control Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2512.09936 |