An Heuristics based Dynamic Power-Aware Resource Allocation for Cloud Computing

Cloud computing is public pools of configurable mainframe system resources and higher-level services that can be rapidly provisioned with minimal running effort, often over the Internet. One of the main challenges in cloud computing is how to reduce the massive amount of energy consumption in cloud computing data centers. The many research authors proposed power aware resource allocation algorithm to solve this issue based on virtual machine allocation and consolidation approaches. The most of existing energy efficient cloud solutions save energy cost at a price of the significant performance degradation. In this paper propose a genetic heuristic search optimization technique based dynamic consolidation of VMs based on adaptive utilization thresholds, which ensures a high level of meeting the service level agreements (SLA).The dynamic virtual machine allocation policy heuristics based on the idea of setting upper and lower utilization thresholds for hosts and keeping total utilization of CPU by all VMs between these dynamic changing thresholds. The power-aware scheduling-based resource allocation (G-PARS) has been proposed to solve the dynamic virtual machine allocation policy problem. The experiments result shows that the proposed strategy has a better performance than particle swarm optimization strategies, not only in high QoS but also in less energy consumption. In addition, the advantage of its reduction on the number of active hosts is much clearer, especially when it is under life-threatening workloads.