Network flow identification method and electronic equipment

An identification method and technology of electronic equipment, applied in network-related fields, can solve the problems of low efficiency of traffic burst perception and inability to adapt to dynamic changes of network traffic, etc., and achieve the effect of sudden and accurate perception

Active Publication Date: 2017-11-17
CHINA SOUTHERN POWER GRID COMPANY
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on this, it is necessary to provide a network flow identification method and electronic equipment for the technical problems that the prior art traffic identification algorithm has low perception efficiency of traffic burst and cannot adapt to the dynamic change of network traffic.

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
  • Network flow identification method and electronic equipment
  • Network flow identification method and electronic equipment
  • Network flow identification method and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Such as figure 1 Shown is a working flow diagram of a network flow identification method of the present invention, including:

[0066] Step S101, calculating the characteristic conditional probability model of multiple training network flows of the same network flow type with respect to different network flow attribute characteristics, the network flow attribute characteristics include Hurst parameter, data packet size attribute and data packet interval time attribute;

[0067] Step S102, receiving the current network flow, and calculating the network flow attribute characteristics of the current network flow;

[0068] Step S103, using characteristic conditional probability models of different network flow types to calculate the corresponding network flow attribute characteristics of the current network flow, and obtain a plurality of current characteristic conditional probabilities related to different network flow types;

[0069] Step S104, using multiple current fea...

Embodiment 2

[0092] Such as figure 2 Shown is a working flowchart of a network flow identification method provided by an embodiment of the present invention, including:

[0093] Step S201, calculating a plurality of network flow attribute characteristics of each training network flow, the network flow attribute characteristics including Hurst parameters, data packet size attributes and data packet interval time attributes;

[0094] For the jth network flow attribute feature ν j and the i-th network flow type K i , calculate the same network flow type K i The same network flow attribute feature ν in multiple training network flows j The average value μ i,j with variance σ i,j ;

[0095] Calculate the i-th network flow type K i The attribute feature ν of the jth network flow of multiple training network flows j The characteristic conditional probability model of is Among them, x is an independent variable, which is used to input the corresponding network flow attribute characteris...

Embodiment 3

[0118] Such as image 3 Shown is a working flowchart of a network flow identification method provided by another embodiment of the present invention, including:

[0119] Step S301, calculating a plurality of network flow attribute characteristics of each training network flow, the network flow attribute characteristics including Hurst parameters, data packet size attributes and data packet interval time attributes;

[0120] Step S302, receiving the current network flow, and calculating the network flow attribute characteristics of the current network flow;

[0121] Step S303, using characteristic conditional probability models of different network flow types to calculate the corresponding network flow attribute characteristics of the current network flow, and obtain a plurality of current characteristic conditional probabilities related to different network flow types;

[0122] Step S304, using multiple current feature conditional probabilities of the same network flow type t...

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 network flow identification method and electronic equipment. The method comprises the steps of: calculating characteristic condition probability models of a plurality of pieces of training network flow belonging to the same network flow type, which are related to different network flow attribute characteristics; receiving current network flow, and calculating network flow attribute characteristics of the current network flow; by using different network flow types of characteristic condition probability models, carrying out calculation on the corresponding network flow attribute characteristics of the current network flow so as to obtain a plurality of current characteristic condition probabilities related to different network flow types; by using a plurality of current characteristic condition probabilities belonging to the same network flow type, calculating a current type condition probability of the current network flow, which is related to the network flow type; and according to the current type condition probability, carrying out identification on the current network flow to obtain an identification result. According to the invention, network flow dynamic behavior characteristics are subjected to quantitative description and then an identification model is established to carry out identification. The method can be suitable for a network flow dynamic changing case, and can carry out accurate perception on high burstiness of network flow.

Description

technical field [0001] The invention relates to the field of network-related technologies, in particular to a network flow identification method and electronic equipment. Background technique [0002] The continuous emergence of new network applications has caused the rapid growth of network traffic. Network traffic involves multiple entities that are closely related to each other, such as computers, network applications, and users. Different network applications have their own specific network traffic behavior characteristics. With the vigorous development of new network applications, network application protocols have emerged, and the complexity of network traffic has increased day by day, showing dynamic, bursty and other behavioral characteristics. In addition, many network security problems caused by computer viruses and malicious network nodes have many impacts on real life. Due to the heterogeneity of network applications, there are many specific types of traffic in ...

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 Applications(China)
IPC IPC(8): H04L12/24
CPCH04L41/142H04L41/145
Inventor 林志达吕华辉黄宏聪
Owner CHINA SOUTHERN POWER GRID COMPANY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap