Joint optimization of Offloading and Resource Allocation in Vehicular Networks with Mobile Edge Computing

Abstract

As a typical application of the technology of Internet of Things (IoT), Internet of Vehicle (IoV) is facing the explosive computation demands and restrict delay constrains. Vehicular networks with mobile edge computing (MEC) is a promising approach to address this problem. In this paper, we focus on the problem of reducing the completion time of Virtual Reality (VR) applications for IoV. To this end, we propose a cooperative approach for parallel computing and transmission for VR. In our proposed scheme, a VR task is divided into two sub-tasks firstly. Then one of the two is offloaded to the vehicle via wireless transmission so that the two sub-tasks can be processed at the MEC server and the vehicle separately and simultaneously. We formulate the scheme as a nonlinear optimization problem to jointly determine computation offloading proportion, communication resource and computation resource allocation. Due to the NP-hard property of this problem, a joint offloading proportion and resource allocation optimization (JOPRAO) algorithm is designed to obtain the optimal solution. Simulation results demonstrate that latency of VR task completion time can be decreased significantly by offloading the task and resource allocation strategy reasonably.