This paper proposes quantum-inspired optimization algorithms for V2X resource allocation, including QAOA variants and quantum annealing emulation. It formulates the V2X resource allocation as a QUBO problem and provides classical emulations. Experimental results show QAOA outperforms classical methods with a 2.38% optimality gap.
Key findings
QAOA achieves an average optimality gap of 2.38%, outperforming classical baselines.
QAOA-based approach maintains sub-second latency, validating quantum-inspired algorithms for vehicular networks.
Classical methods like convex optimization and greedy heuristics show higher optimality gaps.
Limitations & open questions
Future work includes hybrid quantum-classical approaches for larger networks.
Real quantum hardware implementation and dynamic adaptation for highly mobile environments are suggested.