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

Data dimension reduction and feature analysis method in flow analysis

A data dimensionality reduction and traffic analysis technology, applied in the field of computer communication, can solve the problems of strong suddenness and discount of analysis effect, and achieve the effect of accurate analysis

Pending Publication Date: 2019-10-18
INFORMATION & TELECOMM COMPANY SICHUAN ELECTRIC POWER
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Then for the information flow, especially the data flow of the computer network, the flow intensity changes rapidly, the flow change pattern is very diverse and different change patterns are mixed together, there are not only relatively stable change patterns in the flow, but also trend change patterns and cycles At the same time, the suddenness is also very strong. Some bursty traffic even accounts for the main component of the traffic data, while the traffic influencing factors usually only affect a small number of traffic patterns in a few aspects. When these traffic pattern characteristics are mixed together , the analysis effect of the traditional data dimensionality reduction analysis method is greatly reduced

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
  • Data dimension reduction and feature analysis method in flow analysis
  • Data dimension reduction and feature analysis method in flow analysis
  • Data dimension reduction and feature analysis method in flow analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] The flow chart of a data dimensionality reduction and feature analysis method in traffic analysis is as follows figure 1 shown. Firstly, decompose the connotative mode of the load flow data, and then sample the data of each mode at the same time interval as the flow influencing factors to obtain the data sequence of each flow mode, on this basis, establish the data of flow and flow influencing factors The sample matrix of different patterns is analyzed by principal component analysis, so as to obtain the principal change patterns of different patterns. Specific steps are as follows:

[0045] Step 1: Take the flow sequence x(t) as the initial original signal, and perform connotative mode decomposition. First identify all extreme points of the original signal, and fit the upper and lower envelopes e of the signal respectively sup (t), e low (t), calculate the average value of the upper and lower envelopes:

[0046] m(t)=[e sup (t)+e low (t)] / 2 (1)

[0047]Step 2: ...

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 relates to a data dimension reduction and feature analysis method in flow analysis in the field of computer communication, which comprises the following steps of: 1, performing connotation modal decomposition on flow sequence data to obtain a connotation modal function sequence; 2, establishing a sample matrix according to a flow influence factor variable and the connotation modal function; 3, carrying out principal component analysis on the sample matrixes to obtain a principal component variable sequence of each sample matrix, wherein the principal component variable sequencesreflect influence factors of flow change and characteristics of flow. Research results show that compared with a common data dimension reduction and feature analysis method, the method provided by theinvention can analyze influence factors and flow features of flow changes more accurately.

Description

technical field [0001] The invention relates to the field of computer communication, in particular to a data dimensionality reduction and feature analysis method in flow analysis. Background technique [0002] With the rapid development and continuous upgrading of computer networks and wireless communication network technologies, the intensity and types of network traffic continue to increase, and the scale and dimension of data become increasingly complex, forming a massive traffic load. Based on these traffic load data, we hope to find out the influencing factors that affect traffic changes, such as changes in the number of access users in the switch, changes in bandwidth used by users, or traffic scheduling behavior of the switch, or a device failure, or user Changes in habits, or a certain order from the service center or a certain news event, the analysis of these factors affecting traffic can guide the design strategy of resource scheduling in data centers or switches ...

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): G06K9/62G06F16/90
CPCG06F16/90G06F18/2135
Inventor 龚艳徐佳甘炜李嘉周潘可佳刘萧黄林
Owner INFORMATION & TELECOMM COMPANY SICHUAN ELECTRIC POWER