Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A cloud system fault diagnosis method

A fault diagnosis and fault diagnosis model technology, applied in the field of cloud computing, can solve problems such as lack of universality, logs cannot be applied to large-scale concurrent environments, and difficult to apply, achieving high robustness, ensuring diagnostic throughput, and accurate The effect of fault diagnosis and localization

Active Publication Date: 2021-10-15
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing technology either assumes that there are object identifiers in the log and is not universal, or is not applicable to large-scale concurrent environments due to the overlapping and disorder of the log, so it is difficult in a highly complex cloud system application

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
  • A cloud system fault diagnosis method
  • A cloud system fault diagnosis method
  • A cloud system fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0039] The inventors found that the existing log-based diagnosis method first extracts the normal or abnormal features of the system operation from the logs, and completes the fault diagnosis process by comparing the current features with the extracted features. However, the existing methods either have specific requirements for the log format, require the log to contain a specific identifier, or lack good adaptability to high-concurrency environments. The diagnostic accuracy is affected by the number of system log types, log disorder, and log The degree of overlap has a great influence. Among them, the log type refers to the remaining string after removing all the variable parts of the log entry, for...

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 cloud system fault diagnosis method, which divides logs according to generated components, extracts statistical features of logs from the logs of each component, and trains different models for fault diagnosis. In the model training, the present invention uses a deep learning method to learn the time correlation of statistical features, and uses a neural network model to perform dynamic fault judgment. The invention designs and implements an online model update method, solves the problem of incomplete coverage of training data sets, and ensures the diagnosis throughput rate during model update. The invention can provide high-speed and accurate fault diagnosis and location for complex cloud systems.

Description

technical field [0001] The invention relates to the field of cloud computing, in particular to a cloud system fault diagnosis method. Background technique [0002] With the maturity of cloud computing and network function virtualization (Network Functions Virtualization, NFV), commercial cloud systems continue to grow and play an increasingly important role. Typical commercial cloud systems such as Alibaba Cloud, Google Cloud, and Amazon Cloud can provide differentiated services to users on demand. Provide users with a variety of solutions according to their different storage and computing needs. The maturity and development of the cloud system has greatly improved the utilization rate of system resources and reduced operating costs under the premise of ensuring user needs. The flexible resource configuration of the cloud system also brings challenges to its own reliability and stability. Users can complete the dynamic configuration and expansion of resources through the ...

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 Patents(China)
IPC IPC(8): H04L12/24G06N3/04G06N3/08
CPCH04L41/06H04L41/145H04L41/147G06N3/049G06N3/084G06N3/044G06N3/045
Inventor 周朋朋王阳李振宇谢高岗
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com