Research On Resource Allocation Policy For Green Cloud Computing

With the rapid development of the Internet,the scale of the data center is continuously increasing.Constantly updating to IT technology make improvements in the deployment and use of data center infrastructure.However,at the same time,problems such as increased power consumption of data centers have become increasingly prominent.The construction of green and energy-efficient data centers has become an urgent step in the transformation of the information industry.In the data center,the use of virtualization technology for efficient and reasonable allocation and scheduling of resources is a direct means of green energy conservation.The use of virtualization can achieve the purpose of fine-grained physical resources and the sharing of virtual resources.Therefore,making full use of virtualization technology to find a reasonable virtual resource allocation scheme,not only can the data center's resources be efficiently used,but also the energy consumption of the data center can be effectively reduced.The starting point of this paper is to study how to achieve the green energy saving of the data center based on the virtualization technology including static placement of virtual machines and dynamic migration of virtual machines.In a cloud data center,there is usually a large waste of physical resources and link resources,which leads to increased energy consumption.Server consolidation can reduce waste of physical resources.When the virtual machines of a single user request are concentrated to reduce energy consumption,there will be decreased request reliability.This paper considers a single point of failure to ensure the reliability of the requests.Finally,this paper proposes a multi-objective particle swarm optimization algorithm.It takes the physical resource utilization rate and the link loss rate as the optimization targets and uses service reliability and quality of the tenant as constraint conditions.The simulation results show that the method proposed in this paper reliably satisfies the tenant request,effectively controls the link loss in the data center,and significantly reduces the energy consumption of the data center.The use of multi-core processors and advances in virtualization technology have led physical servers to consolidate workloads.However,current virtualization technologies cannot ensure performance isolation between virtual machines,which can lead to performance degradation due to contention for shared resources.Minimizing the performance interference between virtual machines on the same physical machine is a key factor to make servers consolidation successfully.This paper starts from the virtual machine's disturbance degree and the total physical machine disturbance degree,considers the multi-dimensional resource's complementary performance,and proposes a multi-dimensional resource performance interference model.The model can be applied to the instability caused by the dynamic load changes under different conditions.At the same time,a virtual machine migration scheme based on this model is proposed.By using the method of graph-cutting and the method of increasing the minimum total inference degree,complementary virtual machines are tried to be moved to the same physical machine to alleviate the increase in the total interference of the physical machine.At the same time,a verification experiment was performed when the upper and lower thresholds were selected to ensure the rationality of the threshold selection.Experimental results show that the average performance degradation of the proposed algorithm is alleviated,energy consumption is reduced,the number of successfully executed applications increases,the energy efficiency ratio increases,and the stability and time complexity are relatively strong.