Vehicle locus prediction and MEC application migration method based on extreme learning

Abstract

The invention relates to a vehicle locus prediction and MEC application migration method based on extreme learning, and belongs to the wireless communication network field; the method comprises the following steps: S1, using a MEC application to gather, store and process positioning information of a networked vehicle, and building a vehicle local driving locus database; S2, using a local MEC server as the center to reconstruct a vehicle local driving locus, combining an edge network to gather data and dates of adjacent MEC servers, and forming a sample set; S3, using an ELM prediction algorithm to predict a vehicle mobile direction, determining a network vehicle to access the MEC server, and migrating an internet of vehicles application into the server. The method can be applied to pre-migration of the internet of vehicles application deployed based on MEC servers under a mobile edge network scene.

Description

technical field [0001] The invention belongs to the technical field of mobile edge computing in a 5G wireless communication network, and relates to a vehicle trajectory prediction and MEC application migration method based on an extreme learning machine. Background technique [0002] With the rapid development of 5G communication technology and the proposal of Internet of Things (IoV), Mobile Edge Computing (MEC) came into being. MEC is a natural product of ICT industry convergence and mobile network development, aiming to provide an edge network with IT service environment and cloud computing capabilities. MEC has many advantages such as low latency, local perception, and network environment detection, and it has opened up a new market for users and enterprise-level applications. [0003] The Internet of Vehicles (IoV) aims at "smart transportation" and provides new ideas for solving traffic safety problems. It is one of the most valuable MEC applications at present. Appl...

AI Technical Summary

Problems solved by technology

Its disadvantage is that the street segmentation method is not universal, and when the composition of the street scene is more complex, the accuracy of the algorithm will drop sharply

The disadvantage of this patent is that the algorithm based on the Gaussian mixture model has high complexity and only predicts the driving mode of the vehicle in the next few seconds, which is not effective in predicting the driving direction of the vehicle.

Images