Multi-User Offloading and Resource Allocation for Vehicular Multi-Access Edge Computing

By providing computation capability in the vicinity of vehicle terminals (VTs), multi-access edge computing (MEC) enables resource-demanding in-vehicle applications with significantly lower latency and less energy consumption. In this paper, we investigate the problem of offloading decision and resource allocation among multiple VTs to achieve the optimal system-wide user utility. Under the constraints of computation and wireless channel resources and VTs' mobility, this problem is mixed-integer non-linear programming (MINLP), which is generally NP-hard. A heuristic offloading decision method (HODM) is proposed, which decomposes the original problem into two subproblems, i.e., a convex computation allocation subproblem and a non-linear integer programming (NLIP) offloading decision subproblem, and settles them respectively. The convex subproblem is solved with a numerical method to obtain the optimal computation allocation among multiple offloading VTs, and a genetic algorithm (GA) based search algorithm is designed for the NLIP subproblem to determine the offloading decision. Several methods are utilized to reduce the enormous search space of this problem to make our solution more efficient. Extensive simulations are conducted by comparing with four baseline algorithms to demonstrate the superior performance of the proposed HODM.