High-Elasticity Virtual Cluster Placement in Multi-Tenant Cloud Data Centers

Abstract

In recent years, Data Center Network (DCN) has become a promising and efficient data processing infrastructure for cloud computing. One important mission of DCN is to serve the ever-growing demand for computation, storage, and networking for multiple tenants in cloud computing. This paper uses the notion of elasticity to measure the potential growth of multiple tenants in terms of both computation and communication resources. Our objective is to maximize the elasticity for DCNs. We consider the multiple virtual cluster placement problem with the hose model under the computation and communication constraints. We first formulate this problem as an Integer Linear Programming (ILP) problem. Unfortunately, the formulated ILP problem cannot be solved by the simplex or eclipse methods because of a large number of variables and constraints. Therefore, we propose an efficient scheme based on the Dynamic Programming (DP) and analyze its optimality and complexity. Furthermore, we propose a heuristic algorithm for placement that maximizes the elasticity and guarantees the bandwidth demand as well as lower complexity. Extensive evaluations demonstrate that our schemes outperform existing state-of-the-art methods in terms of both elasticity and efficiency.