Optimiziation of VMs and their chains placement

Network Function Virtualization allows operators to deploy network functions in VMs and benefit from on-demand deployment. Placement of VMs and their chains presents multiple challenges. When VMs are placed on hosts in the cloud, existing esource management algorithms assume full knowledge of the system's state. For large clusters, attaining the system's state creates bottlenecks and therefore, placement decisions dominate the time required to deploy network functionalities. Intuitively, placement can be accelerated if the resource management algorithm operates on a cached system state which is not entirely up to date, but in that case, the quality may suffer. We developed a new cache refresh method that achieves an up to 5.3x reduction in placement time with only a slight degradation of quality compared to having the complete and up to date system's state. We also developed a deployment algorithm for service chains that optimizes performance by minimizing the actual cost of virtual switching. This algorithm allows a much higher acceptance ratio of network services when compared to the de-facto standard placement in OpenStack/Nova.