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

Large-scale network traffic abnormality detection method and system

A network traffic, large-scale technology, applied in the transmission system, electrical components, etc., can solve the problem of inaccurate detection methods, and achieve the effects of reducing computing overhead, good detection capabilities, and strong robustness

Inactive Publication Date: 2016-12-07
FUXIN POWER SUPPLY COMPANY STATE GRID LIAONING ELECTRIC POWER +3
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] It can be seen that the various detection methods for traffic anomalies are not yet accurate, and there will be certain shortcomings.

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
  • Large-scale network traffic abnormality detection method and system
  • Large-scale network traffic abnormality detection method and system
  • Large-scale network traffic abnormality detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The specific implementation manners of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0067] The symbols involved in this embodiment are defined as follows:

[0068] f(t): continuous signal;

[0069] S(t, ω): S transform of continuous signal;

[0070] w(t, ω): window function;

[0071] δ(ω): standard deviation;

[0072] F(ω): Fourier transform of f(t);

[0073] h[k]: k point discrete time signal;

[0074] Fourier transform of k-point discrete-time signal;

[0075] f u =(f u1 , f u2 ,..., f uq ): the origin-destination traffic of the u-th group at N discrete time points;

[0076] S u :F u The s transformation;

[0077] N: length of large-scale network traffic;

[0078] w: time window size;

[0079] m=round(N / w): the length of each part of the flow;

[0080] corrf(x, y): Correlation coefficient between x and y;

[0081] d uz : detection threshold;

[0082] A large-scale network traffic anomaly ...

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 present invention provides a large-scale network traffic abnormality detection method and system. The method comprises: obtaining large-scale network traffic in real time; performing partitioned S transform on the large-scale network traffic; and performing large-scale network traffic abnormality detection: reconstructing time domain signals of high-frequency components in origin-destination traffic of each group, calculating an average correlation coefficient of the time domain signals of each group and time domain signals of other groups, and if the average correlation coefficient is less than a set value, the large-scale network traffic is abnormal; otherwise, the large-scale network traffic is normal. The system comprises a traffic obtaining module, configured to obtain large-scale network traffic in real time; an S transformation module, configured to perform partitioned S transform on the large-scale network traffic; and an abnormality detection module, configured to perform large-scale network traffic abnormality detection. According to the large-scale network traffic abnormality detection method and system, network topology information and network traffic are considered, and it is found by means of transform domain analysis that abnormal network traffic has certain high frequency characteristics in a transform domain. A time window is brought into large traffic network analysis, and computation overhead is reduced.

Description

technical field [0001] The invention belongs to the technical field of computer communication networks, in particular to a large-scale network traffic anomaly detection method and system. Background technique [0002] Traffic anomalies exhibit abnormal network behavior, and there are many reasons for this. Abnormal behaviors often cause drastic changes in network traffic, including link traffic and origin-destination traffic. When the network is running abnormally, the network traffic will change abnormally. All of these actions have implications for network activity. Therefore, network traffic anomaly detection is an important task for network management and network operation. [0003] However, performing accurate detection of traffic anomalies is a challenge. Network traffic is difficult to deal with because of its many intrinsic properties. Larger changes often lead to glitches and congested networks. Flow estimation helps to capture the nature of network traffic. ...

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): H04L29/06
CPCH04L63/1425H04L63/1416
Inventor 董宏宇孟凡博路俊海赵宏昊杜春辉王维何凌杰王心贺蒋定德
Owner FUXIN POWER SUPPLY COMPANY STATE GRID LIAONING ELECTRIC POWER