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

Multipath transmission protocol congestion control method based on reinforcement learning

A multi-path transmission and congestion control technology, applied in the field of congestion control, can solve problems such as data packet discarding, network performance degradation, and buffer overflow at the receiving end, achieving fast speed, low prior knowledge requirements, and overcoming packet loss.

Active Publication Date: 2017-09-15
NANJING UNIV
View PDF5 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since MPTCP needs to receive and sort the data of each sub-flow before uploading to the application layer, when the rate difference between MPTCP sub-flows is large, the fast sub-flow needs to "wait" for the data of the slow sub-flow, if the slow sub-flow If the data of the tachyon flow does not arrive for a long time, but the data of the tachyon stream arrives continuously, it is easy to cause the buffer overflow of the receiving end, so that the data packets from the tachyon stream may also be discarded, degrading the network performance

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
  • Multipath transmission protocol congestion control method based on reinforcement learning
  • Multipath transmission protocol congestion control method based on reinforcement learning
  • Multipath transmission protocol congestion control method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0028] figure 2 It is a flow chart of congestion control for multi-path transmission protocols based on reinforcement learning. Firstly, a Markov model is established, and then it is learned repeatedly in the network to obtain the learning results, and finally the results are applied in the network. In this embodiment, we use a simulator to simulate a network environment, and perform the above learning and application process based on the simulated network. The specific process is as follows:

[0029] A) Establish a Markov model, including:

[0030] A1) Define the state of the sender in, is the ratio of the congestion window of the i-th subflow to the total congestion window of n subflows, rtt i / min{rtt} is the ratio of the round-trip time RTT of the i-th sub-flow to the minimum RTT of all sub-flows, ack_ewma is the exponentially weig...

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 multipath transmission protocol congestion control method based on reinforcement learning. A Markov decision process is established to express the congestion control in a form. The current network states of sub-streams are expressed by the sizes of congestion windows of the sub-streams and the RTTs of the sub-streams of a sending end, the action of the sending end to adjust the congestion windows and the sending intervals is defined, and a target equation is established to obtain maximum average throughput and a minimum average throughput. A network model is established to simulate and generate a lot of network environments. In different network environments, all actions are executed on the current network environment by continuous trials and errors, and learning and optimization are realized from the feedback provided by the environment. By means of a lot of offline learning, the sending end can make the corresponding action of adjusting the sizes of the congestion windows and the sending intervals in a certain state area, so that the value of the target equation is the maximum.

Description

technical field [0001] The invention relates to the field of congestion control, in particular to a method for controlling congestion of a multipath transmission protocol. Background technique [0002] Transmission Control Protocol (Transmission Control Protocol, TCP) is a connection-oriented, reliable, byte stream-based transport layer communication protocol. 95% of the traffic in the network comes from TCP connections, and the two ends of the TCP connection generally use one path to transmit data. With the development of multiple access technologies, most of the host computers are equipped with multiple network interfaces, and the network interfaces can also be extended through the USB interface. Moreover, smart mobile terminals are becoming more and more popular, and they often have both a cellular network interface (such as a 3G interface, a 4G interface) and a WiFi interface. The traditional TCP protocol can only bind each connection to a single interface, so it canno...

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): H04L12/24H04L12/707H04L12/751H04L12/801H04L12/807H04L45/02H04L45/24H04L47/27
CPCH04L41/145H04L45/08H04L45/24H04L47/12H04L47/27
Inventor 薛超婧李文中陆桑璐
Owner NANJING UNIV
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