Computation Offloading and Resource Allocation in MEC-enabled Vehicular Networks: Partial Offloading Versus Binary Offloading

By allowing vehicle terminals (VTs) to offload computation tasks to edge servers, mobile edge computing (MEC) effectively alleviates the computational burden on VTs and improves system latency performance in vehicular networks. In this paper, we investigate joint computation offloading and resource allocation problem with different offloading schemes, i.e, partial offloading and binary offloading. We formulate optimization problems to minimize the task completion latency, and obtain the optimal computation offloading and resource allocation solutions. With both offloading schemes, computation offloading and resource allocation algorithms are developed. Numerical results demonstrate that the proposed algorithms exhibit significant latency performance advantages over the benchmark schemes. Additionally, the performances of two offloading schemes are also compared, the results show that partial offloading scheme outperforms binary offloading in latency performances.