Flow control method, device and network equipment

Abstract

The invention provides a flow control method, device and network equipment, wherein the method comprises the following steps of: determining downlink flow and getting the rate of the downlink flow; when the current flow control cycle is achieved, judging whether the flow rate is larger than a preset flow rate threshold or not, if so, increasing the congestion level of the downlink flow, and otherwise, reducing the congestion level of the downlink flow; getting an uplink bandwidth threshold in the current flow control cycle according to the corresponding relation among the congestion level of the downlink flow after increase or reduction, the preset congestion level and the uplink bandwidth threshold; and performing speed limitation on uplink flow corresponding to the downlink flow according to the uplink bandwidth threshold in the current flow control cycle within the current flow control cycle so as to realize flow control. In the technical scheme provided by the invention, the used uplink bandwidth threshold is fixed, thus the uplink flow of a P2P (peer-to-peer) application can be fast controlled, and the flow control rate is improved.

Description

technical field [0001] The invention relates to network communication technology, in particular to a flow control method, device and network equipment. Background technique [0002] Point-to-point (P2P) network transmission protocols are widely used in modern networks. The biggest feature of P2P applications is to occupy as much bandwidth as possible, which makes the bandwidth of other key applications not guaranteed. In order to ensure the bandwidth of other key applications, such as mail service and W3C service, it is necessary to control the flow of P2P applications. [0003] A method of flow control for P2P applications in the prior art is specifically: detecting the actual downlink traffic of network equipment, calculating the error e between the actual downlink traffic and the preset downlink traffic; -Integral-Derivative, PID) control formula calculates the PID output of the error, then calculates the scaling ratio of the upstream traffic according to the calculated ...

AI Technical Summary

Problems solved by technology

[0004] Among them, the PID algorithm is not effective in controlling the "non-linear system", and the P2P application is a typical nonlinear system, and its traffic model changes with the change of resources and online numbers, which causes the PID parameters to be adjusted continuously. Make the control rate of the upstream flow of P2P application slower

Images