Noise-Aggregation–Enhanced Quantum Federated Learning for Transient Stability Assessment of Networked Microgrids

Networked microgrids (NMGs) with low-inertia inverter-based resources (IBRs) require effective transient stability assessment (TSA) approaches to efficiently capture complex system-wide dynamics while preserving the data privacy of local microgrids. This paper developed a Quantum distributed Transient Stability Assessment via Pooling-Assisted Noise aggregation-Enhanced learning (QdTSA-PANE) method, where a quantum federated learning (QFL) framework and training algorithm are designed to leverage the expressibility of quantum operators while simultaneously handling quantum hardware noise and classical measurement noise. QdTSA-PANE introduces three main innovations: (1) a quantum noise aggregation mechanism for characterizing the influence of quantum noise throughout the quantum circuit; (2) a pooling-augmented vertical QFL architecture, with a theoretical proof of its robustness against quantum noise; and (3) a noise-aware learning algorithm that incorporates noise injection during training to improve generalization and enhance robustness under both quantum and classical noises. We validate QdTSA-PANE through extensive experiments on a typical NMG with IBRs. Results show a 46% improvement in test accuracy under realistic noises.