Vehicle-mounted edge network task distribution and unloading method based on deep Q network

Abstract

The invention discloses a vehicle-mounted edge network task distribution and unloading method based on a deep Q network, and the method comprises the steps: firstly carrying out the priority divisionof calculation tasks of different vehicle terminals according to an analytic hierarchy process, and giving different weights to the processing rates of the calculation tasks to establish a relation model; secondly, introducing an edge calculation method based on the deep Q network, establishing a task unloading model with the calculation task processing rate weighted sum as the optimization target, establishing a terminal autonomous optimal task unloading strategy based on the deep Q network, and the long-term stability and effectiveness of an unloading decision making model are guaranteed. Byreasonably distributing and unloading the vehicle-mounted computing tasks, the processing speed of the computing tasks is effectively increased, and therefore the task execution time delay is reduced.

Description

technical field [0001] The invention belongs to the technical field of vehicle networking communication, and in particular relates to a vehicle edge network task distribution and unloading method based on a deep Q network. Background technique [0002] In order to solve the contradiction between the vehicle terminal and the vehicle application, the calculation tasks on the vehicle can be offloaded to the MEC server configured by the RSU, so that the calculation and analysis process of the task can be completed next to the vehicle, and the flexible storage and storage on the MEC server can be deployed. Computing resources can reduce the processing time of computing tasks and vehicle energy consumption. At present, due to the rapid development of vehicle network and other technologies and the increasing amount of data, a large number of vehicle application tasks with high demand for computing resources have emerged, such as automatic driving, intelligent recognition, real-time...

AI Technical Summary

Problems solved by technology

[0003] However, the above method does not perform task priority division for different terminals, so as to realize the optimization of the processing program

At the same time, the above method requires real-time and accurate channel status information, high algorithm complexity, and long iteration steps, which are difficult to meet the needs of low-latency Internet of Vehicles communication systems.

Images