Computation Offloading in Air-Ground Integrated Vehicular Edge Computing Networks

Abstract

The integration of vehicle edge computing (VEC) and air-ground integrated network is considered as a key technology to achieve autonomous driving, where the tasks can be offloaded to the high altitude platform (HAP) through an unmanned aerial vehicle (UAV) as a relay. In this paper, we investigate a joint access equipment selection and resource allocation problem, with the objective of minimizing the total task offloading delay in the air-ground integrated VEC network. Considering the formulated problem is a non-convex problem, we decompose it into three subproblems: access equipment selection, joint bandwidth and computation resource allocation, and UAV trajectory design. Considering the first subproblem is an integer programming problem, the many-to-one matching method is utilized to solve it. Meanwhile, we utilize the CVX package and successive convex approximation (SCA) method to solve the last two subproblems, respectively. Considering the matching externality, we utilize coalition game method to deal with it. Based on the solutions of the three subproblems, the joint computation offloading and resource allocation (JCORA) algorithm has been proposed. Simulation results show that the proposed JCORA algorithm can reduce the total task offloading delay compared with other algorithms.