A virtual machine scheduling method and device based on load balancing

By collecting and sorting resource load data, determining the load balancing value and adaptive function, and optimizing the virtual machine placement scheme, the problem of unbalanced load between the host machine and virtual machines was solved, and load balancing and resource utilization efficiency within the resource pool were improved.

CN115904633BActive Publication Date: 2026-06-19CHINA TELECOM CLOUD TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA TELECOM CLOUD TECH CO LTD
Filing Date
2022-12-29
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing load balancing methods cannot accurately reflect the true resource utilization of the host machine and virtual machines, resulting in unbalanced virtual machine scheduling and affecting overall resource utilization efficiency.

Method used

By collecting resource load data from each host machine in the resource pool, sorting and filtering the data, determining the resource load balance value, calculating the adaptive function value, and selecting the optimal virtual machine placement scheme, load balancing between the host machines and virtual machines can be achieved.

Benefits of technology

It achieves resource load balancing within the resource pool, improves the utilization efficiency of the host machine's central processing unit and memory resources, and optimizes virtual machine scheduling.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115904633B_ABST
    Figure CN115904633B_ABST
Patent Text Reader

Abstract

This application discloses a virtual machine scheduling method and apparatus based on load balancing. The method includes collecting resource load data of each host machine in a resource pool and sorting all host machines; determining a set of virtual machines and, based on the resource load balancing value, obtaining at least two placement schemes for placing each virtual machine in the set among all sorted host machines; calculating the adaptive function value corresponding to each placement scheme, determining the target placement scheme, and scheduling each virtual machine in the set according to the corresponding relationship. By performing load balancing scheduling based on the actual load of the host machines and virtual machines, the resource pool resource load balancing is achieved simultaneously with the load balancing of the host machine's own CPU and memory resources. This method is more effective than current online resource balancing methods based on host machine and virtual machine specifications and can be applied as a resource balancing scheduling algorithm in virtual machine scheduling.
Need to check novelty before this filing date? Find Prior Art