Congestion control method and system based on deep reinforcement learning

A technology of congestion control and reinforcement learning, which is applied in the computer field, can solve problems such as poor control effects, achieve the effects of reducing network congestion, optimizing network performance, and solving poor control effects

Active Publication Date: 2019-12-17
WUHAN UNIV
View PDF8 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of this, the present invention provides a congestion control method and system based on deep reinforcement learning to solve or at least partially solve the technical problem of poor control effect existing in the methods in the prior art

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
  • Congestion control method and system based on deep reinforcement learning
  • Congestion control method and system based on deep reinforcement learning
  • Congestion control method and system based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] This embodiment provides a congestion control method based on deep reinforcement learning, please refer to figure 1 , the method includes:

[0051] Step S1: Initialize the network environment and generate network status data, wherein the network status data includes network delay, transmission rate, transmission rate and congestion window size.

[0052] Specifically, step S1 is to initialize the parameters of the computer network, and then generate network status data.

[0053] During specific implementation, step S1 specifically includes:

[0054] Step S1.1: Establish a connection between the two communicating parties;

[0055] Step S1.2: According to the data sent by the communication parties through the established connection, calculate the network delay, transmission rate, transmission rate and congestion window size.

[0056] Specifically, before the program starts, it is necessary to initialize the network environment, establish a connection between the two par...

Embodiment 2

[0110] Based on the same inventive concept, this embodiment provides a congestion control system based on deep reinforcement learning, please refer to Figure 6 , the system consists of:

[0111]The parameter initialization module 201 is used to initialize the network environment and generate network state data, wherein the network state data includes network delay, transmission rate, transmission rate and congestion window size;

[0112] The environment initialization module 202 is used to initialize the parameters of the congestion control model, wherein the parameters of the congestion control model include a reward function, an experience pool size, a neural network structure, and a learning rate;

[0113] The model generating module 203 is used to select the target network state data from the generated network state data, update the parameters of the neural network according to the target network state data, reward function and loss function, and generate different conges...

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 congestion control method and system based on deep reinforcement learning. The congestion control method includes: firstly, initializing the environment and model parametersof a network; and training a congestion control model by utilizing the collected current window, the throughput, the time delay, the data transmission rate and the like in the network, selecting the congestion control model with the minimum model loss function value and the maximum reward function value according to a training result, and deploying the model into the network to perform congestioncontrol. According to the method, the size of the congestion window is dynamically adjusted according to the current network throughput, round-trip time delay and data packet loss rate, so that the data transmission rate is controlled, the network throughput is improved, the data transmission delay and the data packet loss rate are reduced, the network congestion is reduced, and the aim of optimizing the network performance is fulfilled.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a congestion control method and system based on deep reinforcement learning. Background technique [0002] The rapid development of next-generation Internet technology and the rapid increase of Internet applications bring convenience to people's life and improve the quality of experience, but also put forward new requirements for network performance, especially in the aspect of network congestion control. Network indicators such as the number of packets retransmitted over time, the average packet delay, and the percentage of discarded packets, etc., continuously adjust the data sending rate, reduce the occurrence of network congestion, make effective use of network resources, improve network performance, and provide users with High-quality service experience. Computer network congestion control, as an important method to improve network throughput, reduce data transmission del...

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): H04L12/801H04L12/807H04L12/815H04L12/823H04L12/841H04L12/24H04L47/22H04L47/27H04L47/32
CPCH04L47/225H04L47/27H04L47/283H04L47/29H04L47/32H04L41/145
Inventor 王菲廖旭东马成业胡海燕陈艳姣廖崎臣张竞之夏振厂
Owner WUHAN UNIV
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