Traffic Classification-Assisted Multitasking Offloading Strategy in IoV

Mobile Edge Computing (MEC) is one of the key technologies of 5G network, which can better meet the demand of low latency and high reliability of Telematics. However, in a multi-vehicle roadway in a Internet of Vehicles (IoV) scenario, the edge server cannot compute a large number of offloading tasks in a short period of time. In this paper, a joint offloading allocation method with Naive Bayesian combined with reinforcement learning is proposed, which introduces an idle vehicle parked on the roadside as a computational device so that it can perform task offloading together with the edge server and the vehicle terminal device. The offloading problem is formulated as an optimization problem with the objective of minimizing the offloading delay and the energy consumption of the user’s vehicle, and it is further transformed into a Markov Decision Process (MDP). In order to solve the problem in discrete and continuous action space, Parametrized Deep Q-Networks Learning (P-DQN) algorithm is used to solve the problem. Simulation results show that the proposed algorithm exhibits superior performance in terms of task vehicle utility and resource utilization relative to other algorithms.