Research Of Energy Efficiency Optimization-oriented Dynamic Migration Technology For Virtual Machines In Cloud Computing

Cloud computing provides convenient on-demand paid and scalable computing service mode resources, make enterprise and individual can use the cloud computing technology to deal with the needs of different scenarios flexibly in the era of big data. With the development of the society, the requirement of computing power grows rapidly, more and more data centers are built around the world. Each of these data centers has very high energy consumption. With the advent of the era of cloud computing, the high energy consumption of cloud computing data centers has become a prominent problem, how to reduce the energy consumption of cloud computing data center and improve the efficiency of data center has become the research focus of researchers at home and abroad.In a cloud environment, dynamic virtual machine consolidation(DVMC) is an effective strategy that can improve the energy efficiency. But at the same time, in the process of dynamic virtual machine consolidation, the host may be overloaded then reduce service performance and affect the quality of user service, which will lead to the Service Level agreements(SLA) violation and cause an economic loss of Cloud Service providers.To solve above problems, after studying the dynamic migration techniques of virtual machines on the basis of existing research, considering energy consumption as well as customer service quality, this paper put forward a new virtual machine dynamic migration strategy for energy efficiency.In this paper, the main research work and achievements are as follows: first, the existing virtual machine dynamic migration strategies at home and abroad were reviewed and the research and analysis. And then dynamic consolidation process of virtual machines was introduced in detail and analysis the four decision-making tasks of the dynamic virtual machine consolidation process:(1)Overloaded Host detection;(2)The virtual machine which should be migrated selection;(3)Underloaded Host detection;(4) The host which accept the migrated virtual machine selection. According to the above decision tasks, combined with this paper’s ideas, make optimization to existing methods and finally put forward a new virtual machine dynamic migration consolidation for energy efficiency. In the underloaded host detection step, this paper proposes a new method based on the overload upper threshold of host and the average utilization of all active host, which were named Improved Underload Detection(IUD) Algorithm in this paper. And in the migration target host selection step, this paper puts forward a new strategy that based on the average utilization of the data center which were named Minimum Average Utilization Difference(MAUD) policy.Finally, based on real workload data on Planet Lab, experiments have done with the cloud simulation platform CloudSim. The experimental result shows that, the proposed algorithm can reduce the both energy consumption with SLA violation rate of data centers compared with the existing algorithms, achieving good result for improving energy efficiency of data centers.