A hybrid quantum–classical learning architecture for noise-aware inference in distributed systems

This paper presents Q-INTEL, a hybrid quantum–classical architecture for noise-aware inference in distributed cyber-physical systems. It integrates classical feature processing, variational quantum circuits (VQCs), classical optimisation, and edge–cloud orchestration within a five-layer pipeline. Q-INTEL does not introduce new quantum primitives; instead, it combines established encoding, variational-circuit, parameter-shift, and optimisation methods to analyse accuracy, robustness, latency, energy, and distributed operation. Evaluation is conducted entirely through noise-calibrated classical simulation using parameters representative of IBM Eagle-class superconducting devices, with no execution on physical quantum hardware. Latency and energy are analytically modelled rather than directly measured, so energy results represent relative indicators rather than physical consumption. The framework distinguishes batch-level service latency from per-inference analytical latency and identifies metrics as simulation-derived, modelled, or architectural. A quantum key distribution (QKD) synchronisation interface is included only as an architectural component and is not experimentally evaluated. Under the stated assumptions, Q-INTEL achieves favourable accuracy, robustness, latency, and energy-index results compared with the considered CNN and QNN baselines. These findings provide preliminary evidence of architectural feasibility but do not demonstrate quantum advantage. Future work requires physical-hardware validation, stronger hybrid baselines, comprehensive statistical analysis, and testing on domain-specific distributed-sensing datasets to assess practical performance under realistic deployment conditions comprehensively.