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

Application layer multicasting tree constructing method based on two-layer recurrent neural network

A technology of recursive neural network and construction method, which is applied in the field of construction of application layer multicast tree based on double-layer recursive neural network, which can solve the problem that the neural network model is difficult to obtain the solution solution of application layer multicast tree, and unicast routing cannot introduce restrictions And other issues

Inactive Publication Date: 2009-07-22
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Second, restrictions cannot be introduced in the process of solving unicast routing, especially unequal restrictions
[0008] It can be seen from the above that it is difficult to obtain a limited application layer multicast tree solution using the traditional neural network model

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
  • Application layer multicasting tree constructing method based on two-layer recurrent neural network
  • Application layer multicasting tree constructing method based on two-layer recurrent neural network
  • Application layer multicasting tree constructing method based on two-layer recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048]Improving the accuracy of the obtained path is contradictory to the convergence of the final result variable to 0 or 1, but the effects of these two factors in the motion equation are separated from each other, and the cost parameters and constraints are only expressed in the bias term of the neural network, namely I l middle. Therefore, we take the following measures in the specific implementation process: first consider the bias item I l , so that the state of the neural network converges to a certain accuracy in the shortest path and delay constraints, and then the bias term I l Set to 0, so that the state variable converges to 0 or 1. That is, the convergence of the neural network goes through two stages. In the first convergence stage, a method of adaptively modifying the parameters in the loop process is adopted due to the need to satisfy the condition of the degree of connectivity restriction. Each neuron k has a different ρ l value, during convergence, once ...

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

A method of constructing application layer multicast tree based on double layer recurrent neural network determines the corresponding weights and current bias by neuron motion equations corresponding to the energy function, and adjusts the relevant feedback weight and offset to execute iterative computations until the system converges to stable state. In stable state, output of the neuron variable is solution of actual optimization problem. The invention utilizes the ideal of using Hopfield neural network model to solve the optimization problems, but adds with Kirchoff limited condition in double layer recurrent neural network on the basis for improving the validity of solution; adding with LP type non-linear programming neuron satisfies the limited condition in routing solving process; solving the relation of the relative neuron between neuron matrix of single-cast router ensures the optimization of the final multicast routing.

Description

technical field [0001] The present invention is aimed at the research on the construction algorithm of the application layer multicast tree on the overlay network based on the proxy server, and mainly studies how to solve the application layer multicast routing based on the improved double-layer recursive neural network model, which involves the overlay network and the neural network model , multicast routing algorithm and other technical fields. Background technique [0002] Multicast plays an important role in today's Internet applications, such as video conferencing, online on-demand, and interactive games. However, the network-layer multicast solution's protocol dependence on network equipment affects its deployment and implementation in the entire network. Correspondingly, building a virtual overlay network on the Internet and providing an application-layer multicast solution based on this network has attracted more attention because of its simple deployment and no spe...

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 Applications(China)
IPC IPC(8): H04L12/56H04L12/18H04L29/08
Inventor 张顺颐刘世栋王攀
Owner NANJING UNIV OF POSTS & TELECOMM
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