Link performance and flow classification-based SDN data plane failure recovery method

Abstract

The invention relates to the field of communication, and more specifically, relates to a link performance and flow classification-based SDN data plane failure recovery method. The method comprises thefollowing steps of S1. selecting a performance parameter of a standby path, and defining the parameter measuring the link performance; S2. classifying data flows into multiple levels according to QoSrequests of the data flows; and S3. deploying recovery policies for different priorities of data flow. The method can select a standby path with better performance, classify the data flows scientifically, and deploy corresponding recovery policies for different levels of data flow. The average throughput of the recovered data flow is maximized due to selection of the standby path with better performance, and the cost caused by failures is minimized due to classification of the data flow and corresponding recovery policies.

Description

technical field [0001] The present invention relates to the communication field, and more specifically, relates to an SDN data plane fault recovery method based on link performance and flow classification. Background technique [0002] Software Defined Network (SDN, Software Defined Network) is an important new network technology. This technology separates the data forwarding function and the control function of the forwarding node, and the control function is concentrated on a centralized controller. The controller has a macroscopic view of the entire SDN network and provides a programmable interface to control the entire network. The SDN network is programmable, and network managers can control the behavior of network components through programming, which enables the network to quickly restore communication after a failure occurs. After a failure is detected, the flow table rules pre-deployed according to the recovery strategy are triggered, and the data packets arrive at...

AI Technical Summary

Problems solved by technology

[0011] The above document schemes 2-5 are all active recovery methods. Document 2 mainly relies on the link cost to select the backup path to achieve load balancing, but does not consider other indicators of the link, which may lead to poor overall performance of the backup path and affect failures. Restoration effect, in addition to this, Document 2 does not propose a specific method or indicator for classifying flows, and it configures a 1+1 strategy for the flow with the highest priority (that is, the data flow is transmitted on the working path and the backup path at the same time, and the working path Failure will not interrupt data communication), too much waste of bandwidth resources

For Document 3, the expansion complexity of the OpenFlow protocol is too high, and Document 3 and Document 4 did not consider the importance of data flow when deploying the backup path. All data streams deploy the same recovery strategy, which increases the resources required for recovery.

For Document 5, the selection of the backup path does not take into account the various indicators of the link

Images