Virtual Machine Resource Allocation in Cloud Computing via Multi-Agent Fuzzy Control

Abstract

Dynamic resource (re)-allocation for virtual machines in cloud computing is important to guarantee application performance and to reduce operating costs. The problem is to find an adequate trade-off between these two conflicting goals. An approach is presented to support the Virtual Machine Monitor in performing resource allocation of VMs running on a physical machine of a cloud provider by expressing the two objectives in a utility function and optimizing this function using fuzzy control. To potentially work for an increased number of virtual machines, a multi-agent fuzzy controller is realized where each agent optimizes its own local utility function. The multi-agent fuzzy controller is empirically compared to a centralized fuzzy controller and an adaptive optimal control approach. Experimental results show the effectiveness of the multi-agent fuzzy controller in finding an adequate trade-off between performance and cost.