Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A simulation cloud platform load scheduling system and method based on user feature prediction

A technology of user characteristics and load scheduling, applied in the field of spacecraft simulation cloud platform, can solve the problems of user task distinction with different characteristics, only considering global container resource allocation, low node resource utilization, etc., to reduce low resource utilization and meticulous Reasonable weight calculation and the effect of improving the scheduling scheme

Active Publication Date: 2019-06-21
CHINA ACADEMY OF SPACE TECHNOLOGY
View PDF10 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The problem solved by the technology of the present invention is: to overcome the deficiencies such as the low utilization rate of node resources easily caused by the existing spread strategy, and too many tasks of a single node of the binpack strategy, and provide a load balancing scheduling system and method based on user characteristic prediction of the simulated cloud platform, Solve the problem existing in the current server cluster scheduling strategy that only considers the resource allocation of global containers and does not distinguish user tasks with different characteristics in the platform

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 simulation cloud platform load scheduling system and method based on user feature prediction
  • A simulation cloud platform load scheduling system and method based on user feature prediction
  • A simulation cloud platform load scheduling system and method based on user feature prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] 1. Implement platform construction

[0046] Establish a server cluster, the cluster node information is as follows:

[0047]

[0048]

[0049] The server cluster includes 1 management node and 7 computing nodes.

[0050] 1. The cluster management node is configured with Centos 7.0 system to control the entire server cluster; deploy cluster command (receiving, sending, execution) modules, computing node resource collection modules, computing node screening modules and cluster load balancing scheduling modules.

[0051] 2. The cluster computing node is configured with Centos 7.0 system, which is used for server cluster computing resource supply, and the computing node resource status acquisition module and computing node instruction (receiving, executing) module are deployed.

[0052] 3. The entire server cluster communicates with each other through the TCP / IP protocol to form a local area network (LAN), and exchanges information through the Docker engine.

[0053...

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 simulation cloud platform load scheduling system and method based on user feature prediction. The system comprises a cluster computing node resource collection module, a cluster computing node filtering module and a cluster load balancing scheduling module. The cluster computing node resource collection module is used for continuously summarizing each computing node in the cluster in real time; The cluster computing node filtering module is used for performing statistical analysis on the data collected in the cluster computing node resource collection module to realize historical data-based user feature prediction; And the cluster load balancing scheduling module selects the node with the maximum characteristic weight value as a user container host machine according to the current real-time resource use condition of each node acquired by the cluster computing node resource collection module to complete resource scheduling.

Description

technical field [0001] The invention relates to a simulation cloud platform load balancing scheduling system and method based on user characteristic prediction, and belongs to the field of spacecraft simulation cloud platforms. Background technique [0002] With the development of cloud computing technology, cloud-based modeling and simulation can provide computing power to users on demand in the form of services, becoming a new implementation form of service-oriented modeling and simulation. The mission deduction and technical verification public service platform for space vehicle on-orbit service and maintenance (hereinafter referred to as the public service platform) takes on-orbit service as the application background, integrates flight mission planning and deduction, operation mission planning and deduction, detection and identification task deduction and Many types of simulation tasks such as virtual experiments involve multiple disciplines. The application of advanced...

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): G06F9/50G06F9/455
Inventor 石佳卉李志张志民蒙波黄剑斌黄龙飞韩旭
Owner CHINA ACADEMY OF SPACE TECHNOLOGY
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
Eureka Blog
Learn More
PatSnap group products