Hosting Virtual Machines on Distributed Datacenters
Chuan Pham, Nguyen Hoang Khoi Tran, Minh N. H. Nguyen, Jae Hyeok Son, Choong Seon Hong · 2016
Almost of cloud services nowadays are built at top geographically distributed infrastructure for better reliability and performance. These cloud providers need an efficient method to control and direct user workload to suitable datacenter, depending on many factors such as: network traffic cost, operation cost budget, energy consumption, etc. In the virtual machine placement problem, current works mainly focus on the efficiency of packing virtual machines into servers and ignore the distributed scenario of datacenters. In this paper, we consider the problem of placing virtual machines to host applications on a shared resource pool based on distributed cloud platforms. We formulate the problem of hosting virtual machines on distributed datacenters as an optimization problem, and propose a distributed framework DHC that can dynamically direct workload between datacenters to maximize total utility of entire datacenters. We also conduct many case studies to validate our method, and evaluate its effectiveness and practicality, using real-workload traffic traces. The simulation results show that our algorithm can dynamically optimize the total utility, depending on various workload of users.