A virtual machine deployment method based on particle swarm algorithm in cloud environment

Abstract

The invention discloses a virtual machine deployment method based on a particle swarm algorithm in a cloud environment, and belongs to the field of resource scheduling in a cloud computing environment. To solve the problem of only optimizing a single target and lack of consideration of multiple targets; the invention provides a virtual machine deployment method based on a particle swarm algorithm in a cloud environment. The present invention establishes a deployment mapping between a virtual machine and a physical machine at the IaaS layer; the deployment mapping method includes a user-oriented virtual machine deployment method: an improved multi-objective optimization particle swarm based on congestion judgment after receiving a user application for a virtual machine The algorithm is deployed on the target physical host; the platform-oriented virtual machine dynamic management method: after deploying the virtual machine to the target physical host, it is judged whether the status of the target physical host exceeds or falls below the normal threshold, and the improvement based on the degree of sharing The target optimization particle swarm algorithm determines the mapping relationship between the target physical host and the virtual host. The invention is used to deploy the virtual machine on the target physical host.

Description

technical field [0001] A virtual machine deployment method based on a particle swarm algorithm in a cloud environment, which is used to deploy a virtual machine on a target physical host, belongs to the field of resource scheduling in a cloud computing environment, and particularly relates to an improved multi-objective optimization based on particle swarm optimization Algorithmic virtual machine deployment method. Background technique [0002] The cloud environment is based on a variety of technical support, which is developed from distributed computing, parallel processing, and grid computing. Cloud services are mainly provided by the cloud data center. Through virtualization technology, the large-scale high-performance target physical hosts, network devices, and storage devices contained in the cloud data center are virtualized into a large-scale virtual resource of computing, bandwidth, and storage. pool. [0003] The essence of virtualization technology is to decouple...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to solve the problem that the deployment of virtual machines in the prior art only optimizes a single target, and the algorithm for optimizing a single target is not flexible enough to cope with the large-scale heterogeneous cloud data center deployment environment and the dynamic needs of users; the original algorithm and It is necessary to establish a mapping relationship between practical problems. If the establishment is not good, it is easy to quickly converge to the local optimum, which will affect the accuracy of the algorithm; while only optimizing a single target, there is a lack of comprehensive consideration of multiple targets and consideration of practical applications. problem; the present invention provides a virtual machine deployment method based on particle swarm algorithm in cloud environment

Images