Application Classification Based On Preference For Resource Requirements In Virtualization Environment And Virtual Machine Placement Strategy

In recent years,cloud computing technology has received more and more extensive attention and has become an important research direction in the current academic and industrial.Virtualization technology has many advantages such as server consolidation,improved resource utilization,high availability,flexible deployment,and reduced hardware investment.It has played an important role in cloud computing data center performance improvement and resource optimization,and has become a key technology in the current cloud computing field.The placement strategy of virtual machines in cloud data centers has become an important research.The main strategy is to use appropriate algorithms,how to quickly place the virtual machines on physical machines,and make virtual machines run efficiently on server clusters.However,the virtual machine placement algorithm usually does not consider the type of virtual machine,there exists many problems such as physical machine load imbalance,resource utilization is not high,so we need to choose a suitable virtual machine placement algorithm to balance the physical machine load,and improve resource utilization.In order to solve the above problems,this paper first proposes an application classification method according to the characteristics of resource requirements.And then according to the application classification type,considerind the resource constraints,type of task and resource equilibrium factor,we propose load balancing virtual machine deployment algorithm based on Ant Colony Optimization.The main research work includes the following:(1)Different applications have different preferences for resource requirements.In virtualization environment,if multiple virtual machines hosted on the same server have the same resource requirement preference,performance can be greatly affected for the resource competition between virtual machines.In this paper,we propose an approach to use a feature weighting naive Bayes classifier with Laplacian correction model to classify the applications according to the characteristics of application accessing to CPU,memory,hard disk,and the L2 cache collected using profiling.Based on the application classification,the virtual machines running applications of different types can be deployed on the same physical host.The experiments show that this method can ac hieve high classification accuracy.And this methods avoids the performance bottleneck due to the competition of resources to a certain extent.(2)In order to make full use of the underlying physical resources,this paper proposes an ant colony optimization-based virtual machine placement strategy based on the type of application.Because different virtual machines have different resource requirements,when designing ant colony algorithms,we try to avoid the same resources according to the application type.The demand type virtual machine is placed on a physical host.In the ant colony optimization algorithm,the transfer function,the pheromone initialization,and the pheromone update method are all improved.The algorithm considers resource constraints,load balancing,task types and other factors.Finally,the simulation experiment was performed on the CloudSim simulation platform and compared with other placement algorithms.The experimental results show that this algorithm makes the physical machine of the cloud data center have a lower load imbalance and improves resource utilization.