Effective Capacity Maximization in beyond 5G Vehicular Networks: A Hybrid Deep Transfer Learning Method

How to improve delay-sensitive traffic throughput is an open issue in vehicular communication networks, where a great number of vehicle infrastructure (V2I) and (V2V) links coexist. To address this issue, paper proposes employ hybrid deep transfer learning scheme allocate radio resources. Specifically, the maximization problem first formulated by considering interchannel interference statistical delay guarantee. The effective capacity theory then applied develop power allocation on each channel reused V2I V2V link. Thereafter, proposed obtain optimal assignment for Simulation results validate that provides close performance guarantee compared globally scheme. Besides, can lower violation probability than schemes aiming maximize capacity.