Unlock instant, AI-driven research and patent intelligence for your innovation.

A packet transmission method and system driven by reinforcement learning and stream coding

A technology of packet transmission and reinforcement learning, which is applied in network traffic/resource management, wireless communication, electrical components, etc., can solve the problem of low bandwidth utilization of packet transmission links, achieve intelligent packet transmission, reduce data transmission delay, and minimize Effect of Decoding Latency

Active Publication Date: 2021-10-12
NANTONG UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to propose a packet transmission method based on reinforcement learning and stream coding drive, to solve the problem of low bandwidth utilization of packet transmission links in existing TCP and QUIC technologies under long and fat wireless links

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
  • A packet transmission method and system driven by reinforcement learning and stream coding
  • A packet transmission method and system driven by reinforcement learning and stream coding
  • A packet transmission method and system driven by reinforcement learning and stream coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be noted here that the described embodiments are only part of the embodiments of the present invention, not all the embodiment. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0044] The present invention proposes a packet transmission method driven by reinforcement learning and stream coding, which specifically includes the following steps:

[0045] S1. Set stream encoding parameters;

[0046] The stream encoding parameter is the seed of the pseudo-random number generator used to obtain the stream encoding coefficients.

[0047] S2. The sending end sends a packet, and the packet is an uncoded sourc...

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 present invention discloses a packet transmission method and system driven by reinforcement learning and stream coding. The packet transmission method specifically includes the following steps: first, initialize parameters related to stream coding, and then estimate the network congestion status at this time according to the feedback from the receiving end And the orderly packet receiving progress of the receiving end, this series of states are used as feature vectors for the model to learn in real time, and then the current behavior is selected according to the reward function, and finally in the process of sending packets, the online training of the sending action of the sending end is realized. The grouping system includes a sender, a receiver, a state space unit, a reward function unit, a value fitting unit and an action selection unit. According to the current network conditions and packet loss rate, the present invention dynamically adjusts the packet sending interval, intelligently selects the sending packet type, realizes joint optimization of stream coding rate control and congestion control, improves network throughput, and reduces data transmission delay , and can adapt to changing link conditions.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a packet transmission method and system based on reinforcement learning and stream coding drive, in particular to a wireless link with a large time-delay-bandwidth product based on reinforcement learning and stream coding drive A packet transmission method and system. Background technique [0002] Wireless fat link, that is, a wireless link with a large delay-bandwidth product, is an important part of the future air-space-ground integrated network. At present, in the fat wireless link, the TCP (Transmission Control Protocol) which is conventionally relied on generally has the problem of low bandwidth utilization. Most TCP variants treat packet loss as a sign of congestion and will reduce transmission rates as a result. However, in wireless links, where data packet loss may be due to random link errors rather than congestion, this implementation would ...

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 Patents(China)
IPC IPC(8): H04W28/02H04W28/06H04W72/12
CPCH04W28/0289H04W28/06H04W72/12
Inventor 张非凡李业
Owner NANTONG UNIVERSITY