A Research of Task-Offloading Algorithm for Distributed Vehicles
Haitao Zhao, Qixing Zhu, Yue Chen, Yinyang Zhu · 2020
The rapid development of intelligent transportation has caused vehicle terminals to generate a large amount of data that needs to be processed in real time. Meanwhile, multiple vehicles with high computing performance have also appeared. However, these high-performance vehicles have not been running at full load all the time. Performance vehicles share computing resources in a way that assists vehicles that cannot complete data processing individually within the allowed delay. This paper proposes to divide the running vehicle into two types: task vehicle and service vehicle. The task vehicle offloads the computing task to the service vehicle under the control of the edge server. At the same time, an algorithm for task offloading is given. In the solution of this paper, the priority of the task is divided first, and the task queue is created based on it; then the inequality constraint problem obtained by modeling the task offloading is converted into an unconstrained problem, and the Newton iteration method is used to find its optimal solution. Simulation results show that the proposed scheme reduces the overall delay of the system to a certain extent, and reduces the probability of task processing exceeding the delayed deadline.