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

Construction method and application of distributed route planning model

A technology for planning models and constructing methods, which is applied in the field of network communication to achieve the effects of reducing computational overhead, facilitating model convergence, and high scalability

Active Publication Date: 2022-07-01
HUAZHONG UNIV OF SCI & TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a construction method and application of a distributed routing planning model to solve the technical problem that the prior art cannot perform routing planning truly and accurately

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
  • Construction method and application of distributed route planning model
  • Construction method and application of distributed route planning model
  • Construction method and application of distributed route planning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] A method for constructing a distributed routing planning model, such as figure 1 shown, including the following steps:

[0050] S1. Build a DRL agent for each router in the network to form a distributed routing planning model; the distributed routing planning model is used to obtain the best next hop of each router node based on the DRL agent, and to obtain the service flow after union. routing sequence.

[0051] Among them, the DRL agent includes a series of GNN models and neural network models;

[0052] (1) GNN model:

[0053] The GNN model is used to aggregate the link state information of each router node and its neighbor nodes in the network based on network topology information by using multiple cascaded graph convolution layers to obtain the local state feature of the router node u where the GNN model is located, and input it to In the corresponding neural network model; the local state characteristics of the router node u include: the characteristics after th...

Embodiment 2

[0091] A distributed routing planning method, comprising: inputting current service flow information and network topology information into the distributed routing planning model constructed in Embodiment 1 of the present invention, and obtaining a routing sequence of the current service flow, that is, the route of the current service flow Planning Strategy.

[0092] Preferably, the above-mentioned distributed routing planning method further includes: performing reinforcement learning on the distributed routing planning model based on the routing sequence of the current service flow, and further optimizing the above-mentioned distributed routing planning model. In addition to the offline learning described in Embodiment 1 of the present invention, the present invention further performs online learning on the distributed routing planning model, which greatly improves the accuracy of the model.

[0093] The related technical solutions are the same as those in Embodiment 1, and ar...

Embodiment 3

[0095] A distributed routing planning system includes: a memory and a processor, wherein the memory stores a computer program, and the processor executes the distributed routing planning method provided in Embodiment 2 of the present invention when the processor executes the computer program.

[0096] The related technical solutions are the same as those in Embodiment 2, and are not repeated here.

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 construction method and application of a distributed route planning model, and belongs to the technical field of network communication. According to the method, a DRL agent is built for each router in a network, and a distributed route planning model is formed; and the DRL agent uses a graph neural network to aggregate and update local feature information according to a graph structure relationship, accurately depicts a relationship between network topologies, takes hidden feature information generated through a plurality of graph convolutional layers and network features as state input of the DRL agent, and selects a probability of forming a next hop of routing through strategy network output. All the DRL agents in the distributed routing planning model cooperate with each other to generate a total routing sequence, and after packet forwarding is carried out in a data plane, the reward of the current flow is calculated according to service requirements, so that the maximization of the accumulated reward of all flows passed by each DRL agent is realized; the distributed route planning model constructed by the method is high in generalization capability, and route planning can be carried out truly and accurately.

Description

technical field [0001] The invention belongs to the technical field of network communication, and more particularly, relates to a construction method and application of a distributed routing planning model. Background technique [0002] In the network, routing refers to the path selection problem of packet forwarding from the source router to the destination router, usually by the routing table for packet forwarding. The most traditional network routing algorithm is the static routing algorithm, also known as the non-adaptive routing algorithm, which requires the network administrator to manually configure the routing table. This method is only suitable for simple or stable networks. For large and complex networks , the difficulty and complexity of its implementation are very high. Another common network routing algorithm is dynamic routing algorithm, also known as adaptive routing algorithm, commonly used distance vector routing algorithm (Distance Vector Routing, DV) and ...

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): H04L41/14H04L45/00H04L45/44G06N3/04G06N3/08
CPCH04L41/145H04L45/44H04L45/08G06N3/08G06N3/045Y02D30/70
Inventor 戴彬伍仲丽黄文睿
Owner HUAZHONG UNIV OF SCI & TECH
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