SDN (software defined network) flow table conflict detection device and method based on deep learning

Abstract

The invention discloses an SDN (software defined network) flow table conflict detection device and method based on deep learning; the device comprises a window splitter module, a deep detecting module, a result analysis module, a sniffer module and a database module; the method comprises the steps of mapping a specific SDN application as specific SDN flow table entry {P} through a strategy mapping module; extracting by the window splitter module, flow table entry {W} of window size suitable for the deep detecting module to process from the database module; entering the flow table entries {P} and {W} into the deep detecting module to carry out flow table conflict detecting; entering the flow tables processed via a conflict detecting module into the result analysis module to carry out analytic judgment. Compared with traditional conflict search algorithms, the device and method employing the characteristics of deep learning abstraction high-level data and automated learning can detect whether super-large-scale flow table entries conflict or not more quickly in case of large-scale application deployment.

Description

technical field [0001] The present invention relates to the technical field of network communication, in particular to a deep learning-based SDN flow table conflict detection device and method. Background technique [0002] As people's demand for network applications increases and the scale of data centers continues to expand, network operators and service providers are facing huge challenges in terms of cost, management, and complexity of traditional network infrastructure. The high cost of traditional network architecture deployment restricts the construction of data centers, and the complexity delays the time to market for new services and applications. The difficulty in managing network equipment in the traditional network architecture further increases the operating costs of enterprises and reduces the response speed of updating the network structure. Faced with the problems of high cost, high complexity, and low flexibility exposed by traditional network architectures...

AI Technical Summary

Problems solved by technology

However, at present, deep learning has not been widely used in the network environment under the SDN architecture, especially the application of deep learning to the security field of SDN

Images