Unlock instant, AI-driven research and patent intelligence for your innovation.

A sdn flow table conflict detection method based on deep learning

A deep learning and conflict detection technology, applied in the field of network communication technology and deep learning, can solve the problem that deep learning is not widely used

Active Publication Date: 2019-07-16
ZHEJIANG GONGSHANG UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A sdn flow table conflict detection method based on deep learning
  • A sdn flow table conflict detection method based on deep learning
  • A sdn flow table conflict detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] The present invention will be further described below in conjunction with embodiment.

[0035] The flow table conflict involved in the present invention can be specifically described as follows:

[0036] When the orchestrator generates a specific flow entry according to a specific business feature, the generated policy may conflict with other existing business policies in the system. As shown in Table 1, there is overlap between strategies 1 and 4, between strategies 2 and 3, and between strategies 5 and 6, and the shapes and behaviors of different strategies conflict with each other, so there are overlaps between these strategies. Conflict issues.

[0037] Table 1 conflict flow entries

[0038]

[0039] (1) The specific implementation of the first level deep learning model

[0040] (1.1) Input and output of the first level deep learning model

[0041] An upper-layer application generates a certain policy, which needs to be delivered to the openflow switch. At th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a SDN flow table conflict detection method based on deep learning. This method uses a two-level deep learning model for conflict detection. The first-level deep learning model detects whether there is a conflict between the new flow table strategy and the existing flow table strategy; the second-level deep learning model determines whether all existing flow table strategies The specific flow table policy that conflicts with the new flow table policy. The present invention utilizes the characteristics of deep learning to abstract high-level data and automatic learning, and compared with traditional conflict search algorithms, it can more quickly detect whether super-large-scale flow entries are conflicted during large-scale application deployment.

Description

technical field [0001] The invention relates to the field of network communication technology and deep learning, in particular to a deep learning-based SDN flow table conflict detection 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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L12/721H04L12/751H04L12/755H04L45/02
CPCH04L45/02H04L45/021H04L45/38H04L45/036
Inventor 李传煌程成金蓉王伟明岑利杰
Owner ZHEJIANG GONGSHANG UNIVERSITY