Stochastic VM Multiplexing for Datacenter Consolidation

Abstract

Virtual machine (VM) placement for Datacenter (DC) consolidation is a challenging problem, particularly in the face of VM workload fluctuation. In this paper, we present a stochastic model for optimization of DC consolidation and propose intelligent strategies for statistical VM multiplexing on physical machines (PMs) to ensure optimal use of hardware resources, while providing a service guarantee. We have provided an optimal strategy by modeling and solving the problem as a stochastic integer programming problem followed by a more scalable strategy based on a greedy heuristic. Extensive simulation based experimental results show that the strategies are more efficient in resource utilization while providing bounded service guarantees, than the traditional way of VM placement without any consideration to workload fluctuation.