A data transmission method, a sending node, a receiving node and a data transmission system

Abstract

The invention discloses a method for accelerating data transmission and related devices and systems, wherein the method includes: a sending node sends data packets to a receiving node at a specific rate, wherein each data packet carries a random sequence number and a The receiving node quickly judges the lost data packet according to the double sequence number of the received data packet, and feeds back the sequence number information of the lost data packet to the sending node to instruct the sending node to retransmit the lost data packet. The solution of the present invention can improve the network throughput / transmission rate in a network with high delay and high packet loss rate, and the high throughput rate / transmission rate will not change drastically due to certain network jitter.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a method for accelerating data transmission and a related device and system. Background technique [0002] In network communication, how to ensure reliable and efficient data transmission on the network has always been the focus of research in academia and industry, and the efficiency of data transmission is directly related to the performance of network protocols. Among them, throughput / transmission rate is used to It is one of the important indicators to measure the performance of network protocols. In an existing communication network, TCP (Transmission Control Protocol, Transmission Control Protocol) or UDP (User Datagram Protocol, User Datagram Protocol) is usually used as a transport layer protocol. TCP and UDP are the two most common transport layer protocols in the TCP / IP model. According to statistics, at present, more than 90% of global Internet data tr...

AI Technical Summary

Problems solved by technology

According to statistics, at present, more than 90% of global Internet data traffic is transmitted through TCP, and less than 10% is transmitted through UDP.

However, the Learning-based TCP acceleration technology needs to rely on the study of historical records to understand the current network situation, but for networks with random packet loss and large delay jitter, this learning / judgment effect is not obvious, making the network throughput rate / The increase in transfer rate is not significant

[0007] To sum up, the throughput / transmission rate of the existing transmission protocols still has a lot of room for improvement. Although there are some acceleration algorithms that can accelerate to a certain extent, the development trend of the network is that the traffic characteristics are becoming more and more complex and difficult to achieve. Prediction, especially in scenarios with high latency, high packet loss, and high bandwidth-delay product, the characteristics of the network path are constantly changing, so the acceleration effect will fluctuate, and sometimes even reverse the effect

Therefore, the throughput / transmission rate of the transport layer protocol in the prior art still needs to be improved

Images