Quantum Inspired Vehicular Network Optimization for Intelligent Decision Making in Smart Cities

Connected and automated vehicles require city-scale coordination under strict latency and reliability targets, yet many solutions optimize communications and mobility separately, resulting in degraded performance during outages and under edge–cloud computational contention. This work introduces QIVNOM, a quantum-inspired framework that jointly optimizes V2V/V2I communication and urban traffic control on classical edge–cloud hardware (without a quantum processor). Candidate routing–signal plans are encoded as probabilistic superpositions and updated using sphere-projected gradients with annealed sampling to minimize a regularized cost. An entanglement-style coupling regularizer links networking and mobility decisions, while Tchebycheff multi-objective scalarization with feasibility projection enforces latency and reliability constraints. Robustness is enhanced by chance constraints and Lyapunov-drift control. Plans are mapped to fog nodes through entropic optimal transport, and vehicle-level CVaR (Conditional Value at Risk) micropolicies align local safety with global guidance. In METR-LA-calibrated SUMO–OMNeT++/Veins simulations over a 5×5 km urban map with IEEE 802.11p and 5G NR sidelink, QIVNOM reduces the mean end-to-end latency to 57.3 ms (≈20% below the best baseline). Under incidents, the latency is 62 ms vs 79 ms (−21.5%), and with RSU outages, 67 ms vs 86 ms (−22.1%). Packet delivery averages 96.7% (+2.3 pts), reliability reaches 96.7% in general (RSU-outage 96.8% vs 94.1%), and corridor-closure travel metrics improve (ATT 12.8 min/33% vs 14.5 min/37%).