Energy-Aware VM Consolidation in Cloud Data Centers Using Utilization Prediction Model
Abstract
Virtual Machine (VM) consolidation provides a promising approach to saving energy and improving resource utilization in data centers. Many heuristic algorithms have been proposed to address the consolidation of VM as a vector bin-packing problem. Energy-aware VM Consolidation in Cloud Data Centers Using Utilization Prediction Model The existing algorithms, however, focused mostly on the number of active physical machines (PMs) minimization according to their current resource requirements and neglected future resource demands.
Therefore, in data centers, they generate unnecessary Energy-aware VM Consolidation in Cloud Data Centers Using Utilization Prediction Model migrations and increase the rate of violations of Service Level Agreement (SLA). To address this issue, we propose a consolidation approach to VM that takes into account both the current and future use of resources. Our approach uses a model based on regression to approximate the future use of VMs and PMs for CPU and memory. Using Google cluster and PlanetLab real workload traces, we investigate the effectiveness of the prediction of virtual and physical resource utilization in VM consolidation performance.
System Configuration
H/W System Configuration
Speed : 1.1 GHz
RAM : 256 MB(min)
Hard Disk : 20 GB
Floppy Drive : 1.44 MB
Key Board : Standard Windows Keyboard
Mouse : Two or Three Button Mouse
Monitor : SVGA
S/W System Configuration
Platform : cloud computing
Operating system : Windows Xp,7,
Server : WAMP/Apache
Working on : Browser Like Firefox, IE
Conclusion
We presented a dynamic consolidation approach for Virtual Machine (VM) in this paper called Utilization Predictionaware VM Consolidation (UP-VMC). As a multi-objective vector bin packing problem, UP-VMC formulates a VM consolidation. To consolidate VMs into the minimum number of active physical machines (PMs), it considers both the current and future use of resources. A regression-based prediction model is used to predict future resource utilization. We also proposed a VM allocation algorithm based on prediction models to further improve the quality of service and minimize the number of migrations.
