A cloud system has to deal with highly variable workloads resulting from dynamic usage patterns in order to keep the QoS within the predefined SLA. Aside from the aspects regarding services, another emerging concern is to keep the energy consumption a...
A cloud system has to deal with highly variable workloads resulting from dynamic usage patterns in order to keep the QoS within the predefined SLA. Aside from the aspects regarding services, another emerging concern is to keep the energy consumption at a minimum. This requires the cloud providers to consider energy and performance trade-off when allocating virtualized resources in cloud data centers. In this paper, we propose a resource provisioning approach based on dynamic thresholds to detect the workload level of the host machines. The VM selection policy uses utilization data to choose a VM for migration, while the VM allocation policy designates VMs to a host based on its service reputation. We evaluated our work through simulations and results show that our work outperforms non-power aware methods that don`t support migration as well as those based on static thresholds and random selection policy.