Research Of The Cloud Computing Platform And Scheduling Scheme Based On Openstack

Cloud computing is a new generation IT model, evolved from grid computing, parallel computing and distributed computing. Through the network the scalable and virtualized IT resources can be provided for users on demand in the form of services dynamically. Currently the cloud computing is well developed and many related technologies are converging. At the same time, web applications start to popularize with the development of network technology, and many colleges and universities began to information construction. Information construction in colleges and universities has played a role in the education reform, but there are still some problems during the process. Firstly, the waste of server resources is becoming more and more serious with the increased number of servers for the deployment of information systems. Secondly, the problem of energy consumption is becoming worse. As researches show that cost from hardware and power consumption accounted75percent of total cost of the datacenter. Consequently, promoting the integration of school server resources to improve resource utilization and reduce energy consumption is a very realistic research topic.In this thesis, a series of research work about energy-saving scheduling strategy are conducted. Load migration rate and load growth potential of virtual machine are taken into account in the novel virtual machine selection policy. The concentration ratio of virtual machine is concerned in the process of virtual machine placement. Moreover, a cloud platform based on OpenStack is constructed in this paper. New-developed load monitoring module and virtual machine scheduling module are integrated to the cloud platform, which take the novel scheduling policy proposed in this paper to the actual use.Simulations are carried out to evaluate the performance of proposed scheduling policy. The simulation results show that the virtual machine selection policy based on load migration rate can greatly reduce the number of migration, and the virtual machine placement policy based on concentration ratio of virtual machine has a good performance in reducing energy consumption. Besides, the cloud platform built in this paper improved the utilization of server resources and reduced energy consumption without degeneration of quality of service. The work of this paper provided a good environment for the information construction of colleges and universities.