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

Network optimal path selection method based on deep learning

An optimal path, deep learning technology, applied in neural learning methods, data exchange networks, biological neural network models, etc., can solve problems such as high cost and low efficiency, and achieve the effect of improving overall operating efficiency

Active Publication Date: 2017-07-14
ZHEJIANG GONGSHANG UNIVERSITY
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the massive increase of network devices, it will cost a lot to maintain network faults only by manual labor, and the efficiency will become lower and lower.

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
  • Network optimal path selection method based on deep learning
  • Network optimal path selection method based on deep learning
  • Network optimal path selection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] Divide all available paths of the network into N groups, n in each group, and find an optimal path in each group. The optimal path satisfies: the smallest packet loss rate, the smallest end-to-end delay, the smallest number of hops, the largest available bandwidth, the largest throughput rate, and the smallest jitter; the optimal path selection method is specifically:

[0035]Select k=6 weight targets, and specify the multi-target weight sort order of path optimization on the link as follows: packet loss rate>transmission round-trip delay>hop count>throughput rate>available bandwidth>delay jitter. Assuming that in the selection target of QoS routing, P=(p1,p2,p3,...,pi,...,pNn) respectively correspond to the available paths from the source node to the destination node, then the objective function f1(pi) , f2(pi), f3(pi), f4(pi), f5(pi), f6(pi) respectively repr...

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 network optimal selection method based on deep learning. The method comprises the following steps: performing a labeling operation on an acquired network link feature value so as to acquire a supervised learning data set; inputting the acquired supervised learning data set into a deep learning model to train so as to obtain a trained model; inputting a to-be-tested link data into the trained model to obtain an optimal path through an optimal path selection algorithm. By use of the optimal path selection method disclosed by the invention, the deep learning theory is innovatively and successfully applied to the practice of the network optimal path selection, and a good presentation result is obtained, an entire running efficiency of the network can be improved, and a certain push effect is provided for the future intelligent network development.

Description

technical field [0001] The invention is applicable to the optimal path selection problem of a network self-healing system, and relates to a network optimal path selection method based on deep learning. Background technique [0002] With the rapid growth of the Internet scale, the routing and switching equipment at the bottom of the network has reached tens of thousands of units. At the same time, its related network business has become more and more complex. Complicated network services have correspondingly led to various complex network protocols and network management strategies. Debugging the network also becomes increasingly difficult when faults occur in the network. Network protocol factors or human factors may cause different network failures. When the network fails, it will not only affect the user experience and cause the service to be unavailable, but in severe cases, the entire network will be paralyzed. Therefore, ensuring the normal operation of the network ...

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): H04L12/721H04L12/751G06N3/08H04L45/02
CPCH04L45/08H04L45/124G06N3/08
Inventor 周静静鹿如强张胜龙吴晓春王伟明
Owner ZHEJIANG GONGSHANG UNIVERSITY
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