Network dynamic routing calculation method, device and device

A computing method and computing device technology, applied in the direction of data exchange network, digital transmission system, electrical components, etc., can solve the problem that the algorithm cannot respond quickly or effectively, so as to improve the computing speed, reduce the occupation of storage space, The effect of ensuring accessibility

Active Publication Date: 2018-12-18
BEIJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When a link in the network is suddenly disconnected or congested, existing algorithms cannot respond quickly or effectively

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 dynamic routing calculation method, device and device
  • Network dynamic routing calculation method, device and device
  • Network dynamic routing calculation method, device and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Embodiment 1 of the present invention provides a network dynamic route calculation method, see figure 1 The flow chart of the network dynamic routing calculation method shown, the method includes:

[0033] Step S102, judging whether the adjacent node of the current node is the destination node, if yes, selecting the destination node as the next node.

[0034] The current node has at least one adjacent node, and it is judged whether the destination node exists in the adjacent nodes of the current node, and if so, the destination node is selected as the next node, and the routing ends.

[0035] Step S104, if not, respectively calculate the distances between the current node, the adjacent node and the destination node according to the node vector, and obtain the first distance value and the second distance value respectively. The node vector is obtained through machine learning training;

[0036] The node vector is an optimized matrix obtained after machine learning traini...

Embodiment 2

[0081] Embodiment 2 of the present invention provides a network dynamic route calculation method.

[0082] see image 3 In the example diagram of the network dynamic routing calculation method shown, it is now assumed that it is necessary to find a route with router B as the source point and router D as the destination node. The numbers next to the letters in the figure are calculated f(V i ,V D ) values ​​(i=A,B,...,F). Obviously, in the adjacent nodes of B, the distance function formula satisfies f(V B ,V D )>f(V i ,V D ) established node i is closer to the destination node than B. Therefore, finding the address that meets the condition i as the next hop address will make the packet move in the correct direction.

[0083] see Figure 4Another example diagram of the network dynamic route calculation method shown, now suppose that the connection between B and C is suddenly disconnected, as shown in the figure. At this time, the original shortest path B-C-D is disconn...

Embodiment 3

[0085] Embodiment 3 of the present invention provides a feasibility test of a network dynamic routing calculation method, including 4 groups of experiments.

[0086] The first group of experiments is to test the shortest path routing using RBNV (Routing Based on Node Vectors) of the present invention in a small network (100 nodes, the link weight is 1). The experimental results prove that using the vector obtained by node2vec to initialize the node vector can shorten the training time. In addition, when using the sampling method as the training set, using the vector obtained by node2vec to initialize the node vector can improve the accuracy. In the second group of experiments, considering that routing has requirements on link delay in some cases, a small network was used to test the shortest path routing using RBNV in networks with links with different weights. The third set of experiments, in order to prove the availability of RBNV in a larger network, tested RBNV in a medium...

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 provides a network dynamic routing calculation method, a device and a device, which relate to the technical field of the routing calculation method. The method comprises the following steps of: whether an adjacent node of a current node is a destination node is judged; if yes, the destination node is selected as the next node; if not, the distance between the current node or the adjacent node and the destination node is calculated according to the node vector, and the first distance value and the second distance value are obtained respectively; the node vector is obtained by machine learning training; An adjacent node corresponding to a second distance value that is less than the first distance value is randomly selected as the next node. When the link selected by the currentnode in the network is suddenly disconnected or congestion occurs, the invention can quickly select other available adjacent nodes as the next node, the reaction time required is short, and the reachability of the route can still be ensured to the maximum extent.

Description

technical field [0001] The present invention relates to the technical field of route calculation methods, in particular to a network dynamic route calculation method, device and equipment. Background technique [0002] With the great development of emerging networks (such as mobile Internet, Internet of Things, etc.) and the growth of network users, the problems facing the Internet are users' diversified demands for network services and the huge growth of network traffic. Changes in the network environment pose challenges to the development of routing technologies. Research on dynamic routing algorithms that can adapt to changes in network environments such as network traffic and network topology has strong practical significance and practical value in improving network utilization and making routing technology adapt to current network development. At present, the existing commonly used correlation algorithms require each router to obtain the topological information of the ...

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): H04L12/703H04L12/707H04L12/733H04L45/28H04L45/122H04L45/24
CPCH04L45/122H04L45/22H04L45/28
Inventor 姚海鹏刘惠文张培颖吴胜纪哲
Owner BEIJING UNIV OF POSTS & TELECOMM
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