Mobile network edge cooperation cache model construction method based on machine learning

A technology for building methods and models, applied in the field of mobile network edge cooperative caching mechanism

Active Publication Date: 2019-10-08
派欧云计算(上海)有限公司
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a solution for edge cooperative caching in mobile networks. Based on the computing and storage capabilities of base stations at each level, a caching framework for layered cooperation and same-layer cooperation is formed to support large-scale and various

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
  • Mobile network edge cooperation cache model construction method based on machine learning
  • Mobile network edge cooperation cache model construction method based on machine learning
  • Mobile network edge cooperation cache model construction method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The system flow chart of the present invention is as Figure 1~2 shown.

[0031] A method for constructing a communication network model based on mobile edge assisted caching, comprising the following steps:

[0032] Step 1. Establish a network training model based on the content request data sent by the user; that is, the user uses a mobile phone to send a content request (taking video content as an example), and the local usage detection technology (such as field interception, DPI detection) connected to the device is extracted and compared with the video content. Content-related information; the present invention is based on the ZIPF law to model content popularity to user request processing:

[0033]

[0034] where R f Represents the descending rank of content f popularity, and β represents the skewness factor. we assume that

[0035] Step 2, the routing module in the network training model performs base station identification on the content request data sent...

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 mobile network edge cooperation cache model construction method based on machine learning. The method comprises the steps of 1, establishing a network training model according to content request data sent by a user; 2, enabling a judgement routing module in the network training model to carry out base station identification on content request data sent by a user accordingto an adaptive selection action requirement; step 3, enabling an updating module in the network training model to perform cache replacement on the local base station according to replacement action requirements; and 4, repeating the steps 1-3 until the network training model is stable, so that the user access time delay can be remarkably reduced, the cache hit rate is improved, and the backbone network flow pressure is relieved.

Description

technical field [0001] The invention relates to the field of mobile communication, in particular to a machine learning-based mobile network edge cooperative caching mechanism. Background technique [0002] With the rapid development of wireless access technology and mobile devices, Internet services and applications are gradually migrating to mobile networks. Mobile network traffic is experiencing explosive growth. Limited wireless spectrum resources and traditional mobile network architecture are difficult to cope with the explosive growth of mobile traffic. At the same time, mobile users' requirements for business service quality are constantly increasing. The study found that most of the traffic is used to download the same popular content, which brings great pressure and challenges to the mobile network. Repeated content transmission increases the pressure on the backhaul link, wastes network resources, and reduces user experience. Cache technology is widely used, from...

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
IPC IPC(8): H04W24/06H04L12/24
CPCH04W24/06H04L41/145
Inventor 王晓飞李丁李文凯韩溢文王晨阳
Owner 派欧云计算(上海)有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap