LAUSR

Virtual Infrastructures (VIs) emerged as a potential solution for network evolution and cloud services provisioning on the Internet. Deploying VIs, however, is still challenging mainly due to a rigid management of networking resources. By splitting control and data planes, Software-Defined Networks (SDN) enable custom and more flexible management, allowing for reducing data center usage, as well as providing mechanisms to guarantee bandwidth and latency control on switches and endpoints. However, reaping the benefits of SDN for VI embedding in cloud data centers is not trivial. Allocation frameworks require combined information from the control plan (e.g., isolation policies, flow identification) and data (e.g., storage capacity, flow table configuration) to find a suitable solution. In this context, the present work proposes a mixed integer programming formulation for the VI allocation problem that considers the main challenges regarding SDN-based cloud data centers. Some constraints are then relaxed resulting in a linear program, for which a heuristic is introduced. Experimental results of the mechanism, termed as QVIA-SDN, highlight that an SDN-aware allocation solution can reduce the data center usage and improve the quality-of-service perceived by hosted tenants.