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

Container scheduling strategy based on container load prediction

A load prediction and scheduling strategy technology, applied in multi-programming devices, energy industry, resource allocation and other directions, can solve the problems of low maturity, complex resource management, short development time of container cloud, etc., to reduce investment and avoid resource waste , Improve the effect of cluster resource utilization

Pending Publication Date: 2022-08-09
CHINA NAT HEAVY MACHINERY RES INSTCO
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the development time of container cloud is relatively short, its maturity is low, and it faces complex resource management issues

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
  • Container scheduling strategy based on container load prediction
  • Container scheduling strategy based on container load prediction
  • Container scheduling strategy based on container load prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The present invention will be described in detail below with reference to specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0070] like figure 1 As shown, a container scheduling strategy based on container load prediction includes the following steps:

[0071] Ⅰ. Obtain the time series data of all container load values;

[0072] Ⅱ. Build an ARIMA model to predict the linear component in the time series of container cloud resource demand

[0073] After obtaining the time series data of all container load values, build an ARIMA model to predict the linear component in the time series of container cloud resource ...

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 belongs to the technical field of industrial internet edge computing, and discloses a container scheduling strategy based on container load prediction, which comprises the following steps of: acquiring load value time sequence data of all containers; establishing an ARIMA model to predict a linear component in the time sequence of the container cloud resource demand quantity; establishing an LSTM model to predict a nonlinear component in the time sequence of the container cloud resource demand quantity; the fusion of prediction results of the two models is realized by using a CRITIC objective weighting method, and the prediction precision is improved by using error correction; and carrying out a container scheduling strategy based on a container load prediction result. According to the method, the problem that a single prediction algorithm cannot simultaneously solve linear components and nonlinear components in container cloud resource demand data in network collaborative manufacturing is solved, the resource demand in a period of time in the future is predicted, help is provided for container cloud resource scheduling, the prediction accuracy is effectively improved, container cloud resources are conveniently and better managed, and the network collaborative manufacturing efficiency is improved. And the cluster resource utilization rate is improved.

Description

technical field [0001] The invention belongs to the technical field of industrial Internet edge computing, and in particular relates to a container scheduling strategy based on container load prediction. Background technique [0002] Container is a new type of software standard unit, which contains software ontology and various dependencies required for its operation, and can be quickly and reliably deployed to various computing environments. With the gradual formation of the container technology ecosystem, the container cloud based on container technology has also developed rapidly. However, container cloud has a short development time, low maturity, and faces complex resource management issues. For example, enterprises usually have to consider economic cost and company size when purchasing equipment, so they do not have a large number of spare equipment like cloud service providers. For enterprises, the reservation, allocation and recovery of resources have become a very...

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
IPC IPC(8): G06F9/455G06F9/48G06F9/50G06F11/34G06F17/18G06N3/04G06N3/08
CPCG06F9/45558G06F9/4881G06F9/5083G06F9/505G06F11/3452G06F11/3447G06F17/18G06N3/049G06N3/08G06F2009/4557G06F2009/45591G06N3/044Y04S10/50
Inventor 徐江王志超王富强丁小梅冯连强杨展飞
Owner CHINA NAT HEAVY MACHINERY RES INSTCO