Online Optimization of VM Deployment in IaaS Cloud

Infrastructure-as-a-Service (IaaS) clouds provide on-demand virtual machines (VMs) to users. How to improve the quality of IaaS cloud services is important for service providers. Currently, the VMs in an IaaS cloud are usually deployed with respect to the maximum utilization of resources. In this paper, we propose an online VM optimization method for IaaS clouds. Our method mainly optimizes the VM deployment in IaaS clouds according to the traffics among VMs. VMs are allocated with respect to cabinet capacities at the beginning. At runtime, we monitor the traffics among VMs to get the traffic topology, based on which related VMs are migrated to neighbors to improve performance and reduce the traffics across cabinets. Preliminary simulation experiments are conducted on a well-know simulator, and the experimental results indicate that our method is effective and promising.