Flow detection and control mechanism capable of realizing application perception under SDN and method

Abstract

The invention provides a flow detection and control mechanism capable of realizing application perception under the SDN and a method. The mechanism comprises an application perception module used for analyzing content of a data packet, expanding the data packet information to an application layer, sharing the valuable data packet characteristic information and carrying out consistency maintenance, and a flow control module used for detecting and classifying flows in combination with a network state and the deep data packet characteristics, providing different service for different application programs through dynamically configuring an OpenFlow flow table and processing abnormal flow perception and attacks. According to the mechanism, on the basis of comprehensively evaluating the network state and the flow behavior characteristics, flow application perception is realized, so different flow scheduling strategies are employed to alleviate possible congestion of the network, network load capability is improved, and actual demands of the different application programs are satisfied.

Description

technical field [0001] The invention relates to a traffic detection and control mechanism and method capable of realizing application awareness in an SDN network. Background technique [0002] Traffic monitoring is of great value to network management tasks such as improving overall network performance and network security. On the one hand, dynamic changes in network topology may lead to congestion. Traffic monitoring can reasonably schedule data packets, optimize their routes to alleviate congestion, reduce delays, and increase network throughput to improve network performance; on the other hand, Based on the specific requirements of different applications, combined with the relevant information of network status and data packet characteristics, data packets are classified, identified, and forwarding strategies are adjusted to provide differentiated services for different applications to meet their QoS requirements to the greatest extent. ; In addition, by collecting and a...

AI Technical Summary

Problems solved by technology

However, the data domain of the flow table defined by the OpenFlow protocol only covers the first to fourth layers of the OSI (Open Systems Interconnection, which defines the standard for interconnecting different computers) model, and only evaluates the data packet based on the relatively limited information in the flow table. The implementation of corresponding flow control will not only ignore the deep characteristics of the data packet, and fail to meet the fine-grained and differentiated control requirements of different applications for traffic, but also reduce the accuracy and accuracy of abnormal traffic perception due to the failure to analyze the content of the data packet. Sensitivity, which is not conducive to timely detection and response to network security threats

Images