Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A collaborative online video edge caching method based on federated learning

An edge caching and collaborative technology, applied in the field of cloud-side collaboration edge caching, can solve the problem that the data requirements of deep learning models cannot meet the actual application scenarios, reduce user waiting time and backhaul traffic, and ensure prediction accuracy. , the effect of improving the cache hit rate

Active Publication Date: 2022-03-15
JIANGNAN UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the idealized data requirements based on the distributed deep learning model cannot meet the actual application scenarios.

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 collaborative online video edge caching method based on federated learning
  • A collaborative online video edge caching method based on federated learning
  • A collaborative online video edge caching method based on federated learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This embodiment provides a method for collaborative video edge caching based on federated learning. According to the method for collaborative video edge caching based on federated learning in this embodiment, the specific technical solution is as follows:

[0058] A collaborative online video edge caching method based on federated learning. Participating objects include multiple users, multiple edge nodes, and a central server. Multiple edge nodes use wireless cellular networks as movable Multiple users provide services and are connected to the central server through a backhaul link, and each edge node is configured with an edge server with computing and storage capabilities. The method includes the following steps:

[0059] Step 1, establish a network model based on multiple users, multiple edge nodes and central servers of participating objects, see Figure 1;

[0060] Step 2, using an improved federated learning method to establish a prediction model and train the pre...

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 collaborative online video edge caching method based on federated learning. Participating objects include multiple users, multiple edge nodes and a central server, and multiple edge nodes provide mobile multiple users in their coverage areas. service, and connected to the central server, each edge node configures the edge server, the method includes the following steps: Step 1, establish a network model according to multiple users, multiple edge nodes and the central server participating in the object; Step 2, adopt the improved The federated learning method establishes a prediction model and trains the prediction model to obtain the user online video request prediction model; step 3, obtains the user online video request prediction list according to the user online video request prediction model, and multiple edge nodes analyze their regional coverage of users request a list of predictions, which are cached at the edge using collaborative caching decisions. According to the method of the present invention, the predicted model after training can be automatically updated.

Description

technical field [0001] The invention relates to a cooperative video edge caching method based on federated learning, and belongs to the technical field of cloud-edge collaborative edge caching. Background technique [0002] With the development of mobile Internet social platforms and the popularization of smart terminal devices, people's demand for high-quality real-time data has risen sharply, especially for video services such as short videos and live broadcasts. A common way to obtain user needs is to train the prediction model of user online video requests in the cloud computing center. The traditional cloud computing model requires the cloud center to have strong computing and storage capabilities, and the training process requires a large number of user requests The transmission of information to the cloud center will not only occupy network traffic, but may also cause user privacy leakage. If you choose to extend the use period of the forecast model in order to reduc...

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): H04N21/218H04N21/231H04N21/234G06F16/735G06F16/906G06F16/9535G06F16/957G06N3/04G06N3/08G06N20/00
CPCH04N21/2181H04N21/23106H04N21/23406G06F16/9574G06F16/9535G06F16/735G06F16/906G06N20/00G06N3/08G06N3/045
Inventor 李光辉李宜璟
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com