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

Method and system for elastically deploying services based on machine learning

A machine learning and flexible deployment technology, applied in the computer field, can solve the problems of untimely service deployment, waste of manpower and resources, etc., and achieve the effect of accurately deploying service resources, saving and saving service resources and human resources

Active Publication Date: 2022-02-08
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problems of untimely deployment of existing services and waste of manpower and resources, and proposes a method and system for elastically deploying services based on machine learning

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
  • Method and system for elastically deploying services based on machine learning
  • Method and system for elastically deploying services based on machine learning
  • Method and system for elastically deploying services based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] The method for elastic deployment service based on machine learning described in this embodiment is realized based on the following platforms: server resource platform, log collection platform, search engine platform, server monitoring platform and elastic deployment service platform.

[0029] Wherein, the server resource platform refers to a group of servers that can be used to deploy services. The log collection platform refers to the use of the logstash component to collect log information called by the service interface. The search engine platform refers to using the elasticsearch component to search for the required log information. The server monitoring platform refers to the use of zabbix components to monitor the usage information of the server's hardware resources. The flexible deployment service platform means that the server resource platform can issue commands to enable or disable services, as well as configure server resource information and configure issu...

Embodiment 2

[0042] The following examples mainly describe how to dynamically add a service.

[0043] (1), first deploy a service in a group of server resources, its name is spring-boot-fm, this service is used to simulate the dynamic increase of deployment services when the interface access volume increases, and when the interface access volume is low Time to dynamically shut down the service.

[0044] When the user accesses the spring-boot-fm service, the log information of the interface service will be generated, some of which are as follows:

[0045]

[0046]

[0047] (2) The log collection platform is built using the logstash component to collect log information called by the interface of spring-boot-fm. The search engine platform is built using the elasticsearch component to save the data collected by the log collection platform and deploy the service platform elastically Use elasticsearch to retrieve and count the number of spring-boot-fm interface calls per second, and the n...

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 present invention relates to the field of computer technology. The present invention aims to solve the problems of untimely deployment of existing services and waste of manpower and resources, and proposes a method and system for flexible deployment of services based on machine learning. The log information called by the server interface and the usage information of the server's hardware resources when the instructions for opening and closing the service are issued; the log information and the usage information of the hardware resources corresponding to the instructions for opening and closing the service are taken as the samples of machine learning, respectively. Training to obtain the open service model and the closed service model; collect the log information of the server interface call and the server's hardware resource usage information in real time, judge whether to open or close the service based on the open service model and the closed service model, and perform the service according to the judgment result. on or off. The present invention can save service resources and human resources.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and system for elastically deploying services based on machine learning. Background technique [0002] At present, the zabbix monitoring system is generally used to monitor various network parameters and hardware usage of the server. zabbix can only be used to provide the monitoring and alarm function of the server, and cannot solve the problem of service interface response timeout when the number of users of the service skyrockets. When the service The load is too high. If you need to ensure the stability of the service, you need to manually increase the number of service clusters. When the service load is low, you need to manually close some services to reduce the waste of resources. If the operation is based on human judgment Adding or subtracting servers may cause untimely service deployment and waste manpower. Contents of the invention [0003] The pres...

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): G06F9/50G06N20/00
CPCG06F9/5016G06F9/5027G06N20/00
Inventor 秦晓明
Owner SICHUAN CHANGHONG ELECTRIC CO LTD