Networked microgrids (NMGs) with low-inertia inverter-based resources (IBRs) require effective transient stabil ity assessment (TSA) approaches to efficiently capture complex system-wide dynamics while preserving the data privacy of local microgrids. This paper developed a Quantum distributed Tran sient 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 architec ture, 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.
Networked microgrids (NMGs) with low-inertia inverter-based resources (IBRs) require effective transient stabil ity assessment (TSA) approaches to efficiently capture complex system-wide dynamics while preserving the data privacy of local microgrids. This paper developed a Quantum distributed Tran sient 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 architec ture, 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.
The integration of distributed energy resources requires effective distributed transient stability assessments (TSA) that can capture complex stability dynamics through localized data processing. In this paper, we propose a Quantum Vertical Federated Learning (QVFL)-enabled TSA framework. Our core innovation is a quantum average pooling-based distributed TSA method (QdTSA-AP), which enables data-driven transient stability prediction in a resource-efficient manner while being robustness-by-design against quantum noise, thus ensuring practical applicability in the current Noisy Intermediate-Scale Quantum (NISQ) era. Key contributions include: 1) A quantum average pooling method for effective information extraction from local TSA data while minimizing the communication overhead of transferring quantum information; 2) A lightweight noise-robustness evaluation method, which, for the first time, applies the Signal-to-Noise Ratio (SNR) concept from signal processing to assess the noise robustness of QdTSA-AP, which can be generalized to a wide range of quantum machine learning (QML) tasks; 3) A theoretical proof, based on SNR, showing that average pooling enhances the noise resilience of QVFL through its architectural design rather than requiring additional computational overhead. Extensive numerical experiments validate the accuracy and noise robustness of QdTSA-AP and the effectiveness of the proposed average pooling strategy.
Transient stability assessment (TSA) is an indis-pensable routine in power system operation and control. The increasing integration of distributed energy resources highlights the necessity of distributed transient stability assessment which can effectively capture the complicated stability characteristics of the entire power system without compromising the data privacy of individual local subsystems. This paper devises a quantum-enabled distributed transient stability assessment (Q-dTSA) method to enable data-driven transient stability prediction of power grids in a distributed, expressive and privacy-preserving manner. Our contributions include: 1) A quantum federated learning (QFL) architecture, which enables local power grids to jointly realize the data-driven TSA for the entire system using shallow-depth quantum circuits; 2) A distributed quantum gradient descent (d-QGD) algorithm, which supports effective coordination between local subsystems to perform distributed training of the QNNs without leaking local power system in-formation. 3) Extensive experiments in real-scale power grids obtained from both noise-free simulators and noisy IBM quantum computers, which validate the accuracy, fidelity, and noise-resilience of Q-dTSA, as well as its superiority over centralized quantum computing algorithms.
Abstract—Quantum federated learning (QFL) enables clients to train quantum neural network (QNN) models without sharing private data. We find that aggregation in QFL is unstable under heterogeneous data, unreliable communication, variable fidelity, latency, and quantum hardware noise. Moreover, QFL is non-trivial to address because several QNN parameters are periodic angles, and Euclidean averaging often fails to capture the inherent dynamics. We develop a novel self-consistent midpoint aggregation method for the stable design and implementation of QFLs. We combine QoS-aware client weighting, circular parameter aggregation, and bounded midpoint-based update control. We perform several angular tests and experiments on IBM's real Quantum machines for validation, confirming our approach. Extensive evaluations and experiments on medical and financial datasets show improved stability, lower volatility, and competitive accuracy. Index Terms—Quantum federated learning, adaptive aggregation, geometry-aware aggregation, self-consistent midpoint, quality of service, angular aggregation, quantum neural networks.
Advanced Driver Assistance Systems (ADAS) increasingly employ Federated Learning (FL) to collaboratively train models across distributed vehicular nodes while preserving data privacy. Yet, conventional FL aggregation remains susceptible to noise, latency, and security constraints inherent to real-time vehicular networks. This paper introduces Noise-Resilient Quantum Federated Learning (NR-QFL), a hybrid quantum-classical framework that enables secure, low-latency aggregation through variational quantum circuits (VQCs) operating under Noisy Intermediate-Scale Quantum (NISQ) conditions. The framework encodes model parameters as quantum states with adaptive gate reparameterization, ensuring bounded-error convergence and provable resilience under Completely Positive Trace-Preserving (CPTP) dynamics. NR-QFL employs quantum entropy-based client selection and multi-server coordination for fairness and stability. Empirical validation shows consistent convergence with reduced gradient variance, lower communication overhead, and enhanced noise tolerance under constrained edge conditions. The framework establishes a scalable foundation for quantum-enhanced federated learning, enabling secure, efficient, and dynamically stable ADAS intelligence at the vehicular edge
Advanced Driver Assistance Systems (ADAS) increasingly employ Federated Learning (FL) to collaboratively train models across distributed vehicular nodes while preserving data privacy. Yet, conventional FL aggregation remains susceptible to noise, latency, and security constraints inherent to real-time vehicular networks. This paper introduces Noise-Resilient Quantum Federated Learning (NR-QFL), a hybrid quantum-classical framework that enables secure, low-latency aggregation through variational quantum circuits (VQCs) operating under Noisy Intermediate-Scale Quantum (NISQ) conditions. The framework encodes model parameters as quantum states with adaptive gate reparameterization, ensuring bounded-error convergence and provable resilience under Completely Positive Trace-Preserving (CPTP) dynamics. NR-QFL employs quantum entropy-based client selection and multi-server coordination for fairness and stability. Empirical validation shows consistent convergence with reduced gradient variance, lower communication overhead, and enhanced noise tolerance under constrained edge conditions. The framework establishes a scalable foundation for quantum-enhanced federated learning, enabling secure, efficient, and dynamically stable ADAS intelligence at the vehicular edge.
Quantum federated learning (QFL) emerges as a powerful technique that combines quantum computing with federated learning to efficiently process complex data across distributed quantum devices while ensuring data privacy in quantum networks. Despite recent research efforts, existing QFL frameworks struggle to achieve optimal model training performance primarily due to inherent heterogeneity in terms of (i) quantum noise where current quantum devices are subject to varying levels of noise due to varying device quality and susceptibility to quantum decoherence, and (ii) heterogeneous data distributions where data across participating quantum devices are naturally non-independent and identically distributed (non-IID). To address these challenges, we propose a novel integrated sporadic-personalized approach called SPQFL that simultaneously handles quantum noise and data heterogeneity in a single QFL framework. It is featured in two key aspects: (i) for quantum noise heterogeneity, we introduce a notion of sporadic learning to tackle quantum noise heterogeneity across quantum devices, and (ii) for quantum data heterogeneity, we implement personalized learning through model regularization to mitigate overfitting during local training on non-IID quantum data distributions, thereby enhancing the convergence of the global model. Moreover, we conduct a rigorous convergence analysis for the proposed SPQFL framework, with both sporadic and personalized learning considerations. Theoretical findings reveal that the upper bound of the SPQFL algorithm is strongly influenced by both the number of quantum devices and the number of quantum noise measurements. Extensive simulation results in real-world datasets also illustrate that the proposed SPQFL approach yields significant improvements in terms of training performance and convergence stability compared to the state-of-the-art methods.