Method for controlling congestion control by fusing three kinds of information in wired/wireless hybrid network

Abstract

The invention discloses a method for controlling congestion by fusing three kinds of information in a wired / wireless hybrid network. The three kinds of information include packet loss information, RTT (Radiation Tracking Transducer) information and explicit congestion notification information. The method comprises the following steps of: marking a CE (Conformite Europeenne) bit in IP (International Protocol) packet according to the RTS (Ready-To-Send) repeat times of an MAC (Media Access Control) layer by a wireless node; marking the CE bit in the IP packet by a wired router through an array length; processing a received data packet, confirming the carrying capability through an ACK (Acknowledgement) packet and informing a sending end of the network congestion state by a receiving end; and then, comprehensively considering the packet loss information, the RTT information and the explicit congestion notification information for congestion prediction and adjusting a congestion control mechanism according to a prediction result by the sending end. The method provided by the invention judges the congestion by fusing the three kinds of information, effectively distinguishes wireless packet loss and congestion packet loss, improves the utilization and the throughput of the wired and wireless hybrid network with a wireless link as a bottleneck and improves the whole performance of the network.

Description

Technical field [0001] The present invention relates to a congestion control method that integrates three types of information in a wired / wireless hybrid network. The three types of information are packet loss information, RTT information and explicit congestion notification information. Background technique [0002] TCP is a transmission control protocol widely used in the Internet, providing reliable and orderly transmission services between hosts. TCP congestion control is an important factor in its successful application to the Internet. The premise of TCP congestion control is that network congestion becomes the only cause of data loss, that is, as long as the terminal detects data loss, it is considered to be caused by network congestion, so the congestion control mechanism is invoked, which is suitable for wired environments with better link quality of. [0003] However, the direct application of the traditional TCP protocol applied to the wired network in the wireless netw...

AI Technical Summary

Problems solved by technology

In a wireless network, a large amount of data will be discarded due to channel switching, energy fading, interference, etc. These packet losses caused by the wireless environment are also considered by TCP to be congestion and packet loss, thereby reducing the window and causing unnecessary data. The reduction of the sending rate leads to a decrease in bandwidth utilization, an increase in system delay, and a decrease in throughput

In response to the above problems, there are currently various schemes for improving the performance of the TCP protocol in wireless networks, such as TCP-Probing, I-TCP, M-TCP, Snoop, WTCP, ARQ, FEC, etc., but there are still cross-layer communication and redundant communication. Excessive excess data, low success rate of data transmission, etc.

[0005] 2. The bandwidth cannot be adjusted in time according to the network conditions

However, the implementation of these methods is often complicated. In actual deployment, the user transport layer protocol needs to be updated, and some intermediate router methods need to be changed. Therefore, great resistance has been encountered in the promotion process.

[0006] 3. The energy efficiency of TCP in the wireless environment is not high

Although the queue length can better reflect the degree of network congestion in the wired network, it is not suitable for direct measurement in the wireless network for the following two reasons: first, when the queue length on the wireless node becomes longer, the wireless channel has already Severe competitive congestion has occurred, and it is outdated to use congestion control at this time; secondly, there are many interference factors in the wireless channel, resulting in complex state changes on the wireless channel, and it is difficult to accurately describe the real-time state of the network only based on the queue length

Images