Vehicle-mounted network credit priority task unloading method based on federated learning

Abstract

The invention discloses an in-vehicle network credit priority task unloading method based on federated learning. The method comprises the following steps: 1) an EC and a CV respectively send own position information and available resource information to a CC; wherein the EC is an edge cloud server, the CV is a vehicle in a vehicle network, and the CC is a cloud center; (2) when the CV needs to perform task unloading, task unloading information is sent to the DC; wherein the DC is a decision center in the vehicle network; 3) for the current batch of unloading tasks to be processed, the DC obtains the reputation value of each CV sending the unloading tasks from the CC; then, according to the credit value, setting the processing priority of each unloading task, preferentially making a task unloading decision for the unloading task with the high processing priority, and sending the task unloading decision to the corresponding EC and CV; wherein the CC calculates the reputation value of the corresponding CV according to the behavior information of the CV. According to the invention, the reputation value is used in the task unloading decision, so that the decision performance is improved.

Description

technical field [0001] The invention belongs to the field of vehicle networking and privacy security, and in particular relates to a method for unloading vehicle network credit priority tasks based on federated learning. Background technique [0002] With the development of the Internet of Vehicles, more vehicles can be connected to more computing resources through the network, and these vehicles can realize short-distance, low-latency communication through the Internet of Vehicles. In the Internet of Vehicles environment, individual connected vehicles are limited by computing resources and cannot independently complete corresponding computing tasks. Such as autonomous driving, augmented reality, real-time data analysis and other tasks. At the same time, because the cloud computing model is limited by the network distance, it cannot provide low-latency service response for applications. In order to improve the service quality of a single networked vehicle application, a Ve...

AI Technical Summary

Problems solved by technology

However, in a distributed Internet of Vehicles environment, each vehicle is an individual, and due to different reasons, the vehicle has bad behavior; these bad behaviors will affect the overall efficiency of the vehicle edge computing system

Images