Adaptive virtual resource management with fuzzy model predictive control

Authors:
Lixi Wang;Jing Xu;Ming Zhao;José Fortes
Affiliations:
Florida International University, Miami, China;University of Florida, Gainesville, USA;Florida International University, Miami, USA;University of Florida, Gainesville, USA
Venue:
Proceedings of the 8th ACM international conference on Autonomic computing
Year:
2011

Citing 2
Cited 1

SoftUDC: A Software-Based Data Center for Utility Computing

Computer
Automated control of multiple virtualized resources

Proceedings of the 4th ACM European conference on Computer systems

Application-aware cross-layer virtual machine resource management

Proceedings of the 9th international conference on Autonomic computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Resource management in virtualized systems remains a key challenge where the applications have dynamically changing workloads and the virtual machines (VMs) compete for the shared resources in a convolved manner. To address this challenge, this paper proposes a new resource management approach based on Fuzzy Model Predictive Control (FMPC) which can effectively capture the nonlinear behaviors in VM resource usages through fuzzy modeling and quickly adapt to the changes in the virtualized system through predictive control. This approach is capable of optimizing the VM-to-resource allocations according to high-level service differentiation or revenue maximization objectives. A prototype of this approach was implemented for Xen-based VM systems and evaluated using a typical online transaction benchmark (RUBiS). The results demonstrate that the proposed approach can efficiently allocate CPU resource to multiple VMs to achieve application- or system-level performance objective.