Virtual machine fault detection method and system based on data mining

A technology of data mining and fault detection, applied in electrical digital data processing, error detection/correction, detection of faulty computer hardware, etc. The effect of efficiency and accuracy

Inactive Publication Date: 2016-12-07
云南电网有限责任公司信息中心
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Manual direct fault diagnosis depends to a large extent on the experience of the system administrator, and its reliability is difficult to guarantee
Diagnostic errors are hard to spot and correct without a reference

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
  • Virtual machine fault detection method and system based on data mining
  • Virtual machine fault detection method and system based on data mining
  • Virtual machine fault detection method and system based on data mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] A data mining-based virtual machine fault detection method, comprising the following steps:

[0041] 1) Export the historical data in the vCenter database;

[0042] 2) Standardize and reduce the dimensionality of the exported historical data;

[0043] 3) Divide the preprocessed historical data into labeled and unlabeled data samples, and establish a fault diagnosis model;

[0044] 4) Set parameters, use vSphere SDK to collect data, and store the data in the database;

[0045] 5) Read the collected data from the database and perform preprocessing;

[0046] 6) For the preprocessed data, use the fault diagnosis model to process the data;

[0047] 7) Display the analysis results through data visualization.

[0048] Establishing a fault diagnosis model in step 3) of the present invention is specifically: selecting a data analysis mode for main features, and using labeled and unlabeled data samples to train a classifier to establish a fault diagnosis model.

[0049] The ...

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 virtual machine fault detection method and system based on data mining. The system comprises a data collection module, a data analysis module and a display and alarm module. The method comprises the steps that real-time and historical data is collected through VMware vSphere SDK and a vCenter database; a coarse fine granularity combined collection way is used for obtaining data for providing necessary conditions for data mining; multiple algorithms are combined for analyzing mass data to build a fault diagnosis model, the state of a virtual machine is analyzed through a cluster algorithm, and a fault tree is further built for judging the fault type of the virtual machine; nodes with abnormal data mining results are reported to a user, and system conditions are displayed through a topological graph. Through tests, the system can well judge virtual machine health conditions and diagnose the fault type, the performance can sufficiently meet requirements of the user, and the system can be well compatible with other programs. Meanwhile, the system provides a unified solution for virtual machine fault detection.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a virtual machine fault detection method and system based on data mining. Background technique [0002] In the context of the development of cloud computing and big data, a large number of status files and log information generated by virtualized resources will provide a powerful basis for prediction and rapid positioning of cloud platform fault diagnosis and prediction. Fault monitoring for virtual machines is mainly divided into monitoring of single point faults and monitoring of associated faults. A single point of failure means that a virtual machine has abnormal CPU usage, network bandwidth usage, or storage resource usage during a certain period of time. Correlated faults mean that the abnormal behavior of a virtual machine is due to certain behaviors of other virtual machines. In this case, the virtual machine itself that only focuses on the abnormal behav...

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): G06F11/30G06F11/22G06F9/455
CPCG06F11/301G06F9/45558G06F11/2205G06F11/3055G06F2009/45591G06F2201/815
Inventor 耿贞伟孙恒一张莉娜薛永军郭威陈何雄蔡鄂何昱锋杨泳丹
Owner 云南电网有限责任公司信息中心
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