Research On Virtual Machine Integration Optimization Algorithm For Data Center

Data center construction and development will be conducive to the data center of the commercial application and operation,However,in recent years,with the rapid development of cloud computing,through a variety of application of Internet technology to achieve emerge in an endless stream,in order to meet the growing needs of users,the data center continued to expand in size,which brings a series of new problems to the data center,such as energy consumption,performance,safety,management and so on.Especially high energy consumption,and the integration of virtual machine is one of the means to solve the problem of high energy consumption of data center.The idea is to use the virtual machine migration in real time,so that some light load of the physical machine can be switched off or switched to low power mode,and through a specific objective function to find an approximate optimal solution.Based on the analysis of the shortcomings of the existing virtual machine integration algorithm,this paper proposes two improved virtual machine integration algoritlhms:A virtual machine integration algorithm based on multi group ant colony algorithm is proposed.The idea is to reduce the number of physical machines active according to the current demand for resources,through a specific objective function to establish a migration plan,all kinds of the information entropy to determine the exchange of information between ant colony strategy.Through the simulation experiments,the virtual machine integration algorithm based on ant colony system and the virtual machine integration algorithm based on vector algebra are compared respectively.The effectiveness of the proposed algorithm is verified in terms of reducing energy consumption and reducing the number of virtual machine migration.A virtual machine integration algorithm based on culture and multi colony ant colony algorithm is proposed.In this algorithm,the multi ant colony algorithm is put into the population space of the cultural algorithm,and the optimal value of each generation of ants in the population space is introduced into the belief space of the cultural algorithm through the function.Through the evolutionary algorithm in the belief space to evolve the program,by using the least number of migration to make more physical machine into hibernation,to achieve the purpose of reducing the energy consumption of the cloud data center.Simulation results show that the proposed algorithm can not only reduce the energy consumption but also reduce the number of virtual machine migration.