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

Early warning method and system for detecting state of ML standby nodes

A technology of node status and backup nodes, applied in error detection/correction, biological models, instruments, etc., to achieve the effects of simple structure, improved success rate, and reliable design principles

Inactive Publication Date: 2020-05-08
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned prior art of the prior art, there is a defect that the ML function of the entire cluster cannot be guaranteed when the active / standby mode is adopted and the state of the standby node is unpredictable. The present invention provides a detection ML standby node state early warning method and system to solve the above technical problems

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
  • Early warning method and system for detecting state of ML standby nodes
  • Early warning method and system for detecting state of ML standby nodes
  • Early warning method and system for detecting state of ML standby nodes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 As shown, the present invention provides a kind of early warning method that detects ML standby node status, comprises the following steps:

[0065] S1. Collect the physical information and node status of each node in the cluster, and generate a random forest classification model in combination with the random forest classification algorithm;

[0066] S2. Obtain the standby nodes in the cluster through database retrieval, and collect the physical information and actual node status of each standby node;

[0067] S3. Input the physical information of each standby node into the random forest classification model to obtain the predicted node status of each standby node;

[0068] S4. Comparing the predicted node state and the actual node state of each standby node, and giving an early warning to the standby node.

Embodiment 2

[0070] Such as figure 1 and figure 2 As shown, the present invention provides a kind of early warning method that detects ML standby node status, comprises the following steps:

[0071] S1. Collect the physical information and node status of each node in the cluster, and combine the random forest classification algorithm to generate a random forest classification model; the physical information of the node includes the CPU, disk, memory and network information of the node; the node status includes error, good and uncertain ;Specific steps are as follows:

[0072] S11. Collect CPU, disk, memory and network information of existing nodes in the cluster;

[0073] S12. Use the CPU, disk, memory and network information of the existing nodes as the model input column;

[0074] S13. Taking the node state of the existing node as a model prediction column;

[0075] S14. Generate a random forest classification model A according to the model input column, model prediction column and ...

Embodiment 3

[0089] Such as image 3 As shown, the present invention provides an early warning system for detecting the state of ML standby nodes, including:

[0090] The random forest classification model generation module 1 is used to collect the physical information and node status of each node in the cluster, and generate a random forest classification model in combination with the random forest classification algorithm; the random forest classification model generation module 1 includes:

[0091] Existing node physical information collection unit 1.1, used to collect CPU, disk, memory and network information of existing nodes in the cluster;

[0092] The model input column setting unit 1.2 is used to use the CPU, disk, memory and network information of existing nodes as the model input column;

[0093] The model prediction column setting unit 1.3 is used to use the node state of the existing node as the model prediction column;

[0094] A random classification model generating unit ...

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 an early warning method and a system for detecting the state of ML standby nodes, and the method comprises the following steps: S1, collecting the physical information and nodestate of each node in a cluster, and generating a random forest classification model in combination with a random forest classification algorithm; S2, acquiring standby nodes in the cluster through database retrieval, and collecting physical information and actual node states of the standby nodes; S3, inputting the physical information of each standby node into the random forest classification model to obtain a prediction node state of each standby node; and S4, comparing the predicted node state and the actual node state of each standby node, and carrying out early warning on the standby nodes. According to the method, early warning of the ML high-availability standby node is realized, so that the standby node is ensured to be in an available state all the time, the success rate of switching between the main node and the standby node is improved, and the safety and the reliability of ML use of a user are ensured.

Description

technical field [0001] The invention belongs to the technical field of software testing, and in particular relates to an early warning method and system for detecting the state of an ML standby node. Background technique [0002] ML is the abbreviation of Machine Learning, and its learning. [0003] ML (Machine Learning) is a supporting function of the big data cloud platform. It uses memory computing and iterative computing for big data learning, which greatly improves the mining and analysis capabilities of massive data. Traditional statistics or machine learning mostly rely on data sampling and can only be executed on a single machine, making it difficult to accurately reflect the characteristics of the complete set. [0004] The existing technology provides a cluster mode for ML installation. The master-standby mode is adopted. When the master node is down, the standby node is started to take over the business. However, when the status of the standby node is unpredictab...

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): G06F11/30G06F11/32G06N3/00
CPCG06F11/3006G06F11/327G06N3/006
Inventor 李二真
Owner INSPUR SUZHOU INTELLIGENT TECH CO LTD
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