QSTAformer: A Quantum-Enhanced Transformer for Robust Short-Term Voltage Stability Assessment against Adversarial Attacks

TL;DR

QSTAformer introduces a quantum-enhanced Transformer model with adversarial training for robust and efficient short-term voltage stability assessment in power systems, addressing vulnerabilities of classical methods.

Contribution

It is the first to systematically investigate adversarial vulnerabilities of quantum machine learning in STVSA and integrates PQCs into Transformer attention mechanisms.

Findings

Achieves competitive accuracy in voltage stability assessment.

Demonstrates enhanced robustness against adversarial attacks.

Reduces model complexity compared to classical approaches.

Abstract

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.