Network fault early warning method and device

A technology for network faults and failures, applied in data exchange networks, digital transmission systems, electrical components, etc., can solve problems such as different user-level network equipment standards and inability to locate user-level network equipment, and achieve the effect of unified index data

Active Publication Date: 2019-12-20
CHINA UNITECHS
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the defect that the network failure early warning method in the prior art cannot locate the specific user-level network equipment that has failed, and different user-level network equipment adopts different standards, the first aspect of the present invention provides a network failure early warning method. include:

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 fault early warning method and device
  • Network fault early warning method and device
  • Network fault early warning method and device

Examples

Experimental program
Comparison scheme
Effect test

other Embodiment approach

[0068] In other implementations, the process of using the time series forecasting algorithm to predict whether the relevant indicators are abnormal by the abnormal indicator determination module 730 includes: for each relevant indicator, determine the time window, period and forecast point of each period, and take the time of the forecast point for each period Construct time series data from the historical data before and after the window; use multiple time series forecasting algorithms to determine the confidence interval of the prediction point according to the time series data; for each confidence interval, judge whether the true value of the prediction point of the relevant index falls within the confidence interval If not, determine that the relevant index is abnormal; count the number of times that the relevant index is determined to be abnormal, and if the number of times is greater than the predetermined number, then determine that the relevant index is an abnormal index...

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 provides a network fault early warning method and device, and the method comprises the steps: collecting network fault data and network sensing index data; analyzing the correlation between the network fault data and the network sensing index data, and determining related indexes; predicting whether the related index is abnormal or not by utilizing a time sequence prediction algorithm, and if so, determining that the related index is an abnormal index; and for each piece of user-level network equipment, collecting abnormal index data, and if the preset number of abnormal indexesare abnormal, determining that the user-level network equipment has a network fault. According to the invention, the faulted user-level network equipment can be accurately positioned, and the index data used by the network fault early warning of each user-level network equipment is unified, so that the whole network can be covered.

Description

technical field [0001] The invention relates to the field of network fault early warning, in particular to a network fault early warning method and device. Background technique [0002] Existing network fault early warning judges faults by setting thresholds for performance and other index data, and judges equipment faults if the threshold is exceeded. This method has the following defects: 1. It can only be effective for equipment that can collect indicators. For equipment without performance data such as optical splitters, it is impossible to judge equipment failures; 2. Frequent performance collection on equipment will affect the performance of the equipment itself; 3. Existing network fault judgment can only locate a series of faulty devices, and it is impossible to judge which devices are the root cause of the fault; 4. Existing network fault judgment needs to collect different indicators for different devices, and different indicators need to be set differently. The t...

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): H04L12/24H04L12/26
CPCH04L41/06H04L43/08H04L43/16
Inventor 李敏敏
Owner CHINA UNITECHS
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