Mathematical programming for server consolidation in cloud data centers
Bo Wang, Ying Song, Xiao Cui, Jie Cao · 2017
Server consolidation based on virtualization technology simplifies system administration and improves energy efficiency by improving resource utilizations and reducing the physical machine (PM) number in contemporary service-oriented data centers. These benefits prompt service providers to deliver their services on virtualized data centers. For a service provider, their total costs are mainly composed of the investment costs for buying infrastructures, such as the ownership costs of PMs, and the operational costs, such as the electricity costs for powering PMs, cooling, lighting and so on. Plenty work has studied on minimizing the operational costs. On the contrary, we study on the scale planning for minimizing the investment costs for building/updating data centers providing Internet services, in this paper. We model the scale planning as an integer program minimizing the total ownership costs of PMs. Extensive experiments results show that our scale planning is better than the plannings made by static and dynamic consolidations and that using the scale planning improves the computing times consumed by online consolidations without impact on their performance.