Abstract—Availability, as a part of Service Level Agreement (SLA), is a critically important issue in cloud services, which are affected by server or network failures in datacenters. Cloud service providers seek to not only fulfill the SLA, but also simultaneously minimize their operating costs, which are dominated by the energy consumption. In order to minimize the impact of a server/switch failure on a single application, one spread out the VMs for the application across different racks. Although a higher availability can be achieved, the power consumption may increase significantly. In this paper, we develop a variance-based metric to measure the risk of either over provisioning or under provisioning availability by means of VM placement. We then propose algorithms to place VMs in online and offline manners, respectively. These algorithms aim to strike a balance between maximizing the availability and minimizing the energy, in order to reduce the operating cost for the service providers.

Index Terms—Cloud, availability, energy consumption, risk, dual

Cite: Zhouhan Yang, Liu Liu, Sanjukta Das, Ram Ramesh, Anna Ye Du, and Chunming Qiao, "Availability-Aware Energy-Efficient Virtual Machine Placement Algorithm," Journal of Communications, vol. 10, no. 9, pp. 647-658, 2015. Doi: 10.12720/jcm.10.9.647-658