A method for offloading edge computing tasks in Internet of Vehicles

A technology for edge computing and computing tasks, applied in neural learning methods, vehicle wireless communication services, vehicle components, etc., can solve problems such as high-latency computing capabilities, and achieve the effects of large network utility, low latency, and expansion of computing resources.

Active Publication Date: 2022-06-24
SHANDONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The arrival of the 5G era has greatly promoted the development of the Internet of Things era, and opened the door for new network architecture and intelligent services. With more and more smart devices connected to the Internet, the information of a large number of sensor device terminals will be Handed over to the network center for processing, the information needs not only timely processing, but also intelligent data analysis. At this time, the computing resources of traditional base stations and cloud computing can no longer meet the needs of users, because they will have a high delay and limited computing power

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for offloading edge computing tasks in Internet of Vehicles
  • A method for offloading edge computing tasks in Internet of Vehicles
  • A method for offloading edge computing tasks in Internet of Vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0091] The present invention is described in further detail below in conjunction with the accompanying drawings and specific embodiments:

[0092] like figure 1 Shown is a block diagram of the method of the present invention, which includes the following four processes: establishing a new type of scene in combination with the moving vehicle and a parking lot with a reward mechanism; mathematically modeling the scene through the current state; proposing a Combining the objective function of vehicle edge network utility and delay; using DQN to solve the optimization problem of the objective function, the final offloading scheme is obtained. The specific performance is as follows: combining the computing resources of base stations near the cell users, vehicles on the road and vehicles in the parking lot to create a new scenario, expressing the process as a Markov process, and mathematically modeling the created scenario, And combined with the network utility and task processing...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for unloading edge computing tasks in the Internet of Vehicles, belonging to the technical field of mobile communication, comprising the following steps: combining base stations near users in a community, driving vehicles and parking lots with a reward mechanism to establish a new type of scene; through the current Mathematical modeling is carried out on the new scene established by the state; the objective function is established by combining the utility of the vehicle edge network and the task processing delay; the DQN is used to optimize the objective function to obtain the final unloading scheme. The invention solves the problem of task offloading in edge computing, expresses the decision-making process as a Markov process, formulates the problem by setting up an objective function that combines utility and time delay of the vehicle edge network, and uses DQN to solve the optimization problem of the objective function , to get the final unloading strategy. The invention expands the computing resources of the cell, and maximizes the operator's utility under the condition of ensuring the user's online experience.

Description

technical field [0001] The invention belongs to the technical field of mobile communication, and in particular relates to a method for offloading edge computing tasks in the Internet of Vehicles. Background technique [0002] The arrival of the 5G era has greatly promoted the development of the Internet of Things era, and opened the door to new network architectures and intelligent services. Handed over to the network center for processing, this information not only needs to be processed in a timely manner, but also needs to be analyzed intelligently. At this time, the computing resources of traditional base stations and cloud computing can no longer meet the needs of users, because they will have a higher delay. and limited computing power. As a part of the Internet of Things, the Internet of Vehicles also has this problem. [0003] The concept of edge computing has become a key technology to solve this problem. It can offload computing tasks to other places with computin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): H04W4/40H04W28/08G06N3/08
Inventor 陈赓徐先杰曾庆田郭银景孙红雨邵睿张旭
Owner SHANDONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products