Virtual machine energy-saving integration method and system based on hybrid swarm intelligence and storage medium

Abstract

The invention discloses virtual machine energy-saving integration method and system based on hybrid swarm intelligence and storage medium. The method comprises the following steps of: collecting resource occupation information of a data center server, resource request information of a virtual machine and mapping information between the server and the virtual machine by a resource monitor; detecting an overload server according to the CPU utilization rate under the peak performance ratios of the servers of different models; according to the migration value ratio, selecting the virtual machine to be migrated from the overload server for migration; re-setting the virtual machine to be migrated by using a hybrid differential evolution particle swarm optimization algorithm; and according to the CPU load mean value of the cluster, selecting an under-load server to turn off, and replacing the virtual machine in the under-load server by using a hybrid differential particle swarm optimization algorithm. According to the virtual machine integration method, the real-time power consumption of the cluster can be effectively reduced through multi-stage virtual machine scheduling, the number of active servers of the data center and the migration frequency of the virtual machines are reduced, and the service quality of the data center is guaranteed.

Description

technical field [0001] The invention relates to the field of virtual machine scheduling in a cloud data center, in particular to a hybrid group intelligence-based virtual machine energy-saving integration method, system and storage medium. Background technique [0002] With the popularity of IaaS services, the resource requirements of data centers in different business scenarios are increasing, and data centers need to deploy a large number of servers to provide sufficient computing resources and storage resources for cloud services. The energy consumption problem caused by the rapid expansion of server scale has gradually attracted people's attention. The virtual machine integration method can effectively reduce the real-time power consumption of server clusters and ensure the quality of cloud services by integrating virtual machine placement and migration technology, dynamic voltage frequency adjustment technology, and server dynamic shutdown technology. It is a research h...

AI Technical Summary

Problems solved by technology

The virtual machine integration problem is a multi-objective optimization NP-hard problem. These goals are often contradictory: the reduction of real-time power consumption may lead to an increase in the number of virtual machine migrations, and the reduction of the number of active servers and resource fragmentation may cause server overload. rise in probability

However, most of the virtual machine integration methods still have certain deficiencies: the heuristic virtual machine integration method based on the greedy strategy has a single optimization goal, and can only obtain the optimal solution of the sub-stage of the problem during scheduling, and cannot combine the global information of the problem. Virtual machine scheduling; a single swarm intelligent virtual machine integration method often has problems such as premature convergence and local optimum in the iterative process, making it difficult to further reduce the energy consumption of the cluster, and there is still a large room for improvement

At the same time, in order to achieve the purpose of saving cluster power consumption, the existing virtual machine integration methods often lead to a decline in the quality of cloud services and cannot meet customer needs

Images