Cloud data central virtual machine scheduling method based on OpenFlow frame

Abstract

The invention discloses a cloud data central virtual machine scheduling method based on an OpenFlow frame and mainly solves the problem that transfer scheme optimization object under an existing cloud computing data center environment is single. The method includes the steps of firstly, collecting related information of a cloud data central server and a virtual machine through an OpenFlow controller, and analyzing virtual machine load cycles and change conditions; secondly, calculating a new virtual machine position according to an ant colony algorithm based on pheromone diffusion; thirdly, collecting routing information and the new virtual machine information by the OpenFlow controller; fourthly, using a Dijkstra algorithm to calculate an appropriate transfer path to complete virtual machine scheduling according to the routing information and the new virtual machine position. By the method which can be used for scheduling the virtual machine by using the improved ant colony algorithm under the OpenFlow frame, the overall energy consumption of a cloud data center can be lowered, and load balancing can be achieved.

Description

technical field [0001] The invention belongs to the technical field of cloud computing, and relates to a method for scheduling virtual machines in a cloud data center, which can be used to schedule virtual machines using an improved ant colony algorithm under the framework of OpenFlow, thereby realizing overall energy consumption reduction and load balancing of data centers . Background technique [0002] With the rise of a number of new Internet services and the rapid growth of public access bandwidth, data center network traffic is showing a trend of rapid growth. Internet services have put forward higher and higher transmission quality requirements for data centers and even the Internet, including large bandwidth, security assurance, flexible scheduling, and intelligent management. Under this trend, various solutions have emerged. OpenFlow technology is a new network switching model that has emerged as the times require. It completely subverts the original practice of us...

AI Technical Summary

Problems solved by technology

However, this may lead to high resource utilization of a certain server in the data center, affecting the overall performance of the data center

Therefore, if only a single method is used for scheduling, the overall performance of the system cannot be fully considered during scheduling. While optimizing a certain performance indicator, it will cause deterioration of other performance indicators and affect the overall operation of the data center.

Images