Efficient network resource sharing in cloud computing environments is a challenging problem. Additionally, network congestion has been reported as a main bottleneck in multi-tenant data centers. In this paper, the problem of virtual machines allocation is tackled based on Software-Defined Network (SDN) resource allocation strategy. Moreover, several important parameters are taken into consideration that have been ignored in previous related studies. Another important imposing goal of this paper is to minimize the overall cost in cloud computing environments while allocating network resources. Simulation studies have been conducted to evaluate the performance of the proposed strategy. Simulation results show a reduction in the utilization in the valuable upper-layer links in data centers which is resulted mainly from favoring the lower-cost links during the allocation process. Additionally, the proposed strategy is able to cope with the dynamic nature of allocation process. More importantly, it avoids false allocation in cloud computing environments.
Andrew YoungeGregor von LaszewskiLizhe WangSonia Lopez-AlarconWarren Carithers
Ashok Kumar TurukBibhudatta SahooSourav Kanti Addya