Cost‐based placement of vDPI functions in NFV infrastructures

Network functions virtualization (NFV) is transforming how networks are operated and how network services are delivered. The network is more flexible and adaptable, and it can scale with traffic demands. To manage video traffic in the network, or acquire protection from cyber‐attacks, Deep Packet Inspection (DPI) is increasingly deployed at specific locations in the network. The virtual DPI (vDPI) engines can be dynamically deployed as software on commodity servers within emerging network functions virtualization infrastructures. For a network operator, deploying a set of vDPIs over the network is a matter of finding the appropriate placement that meets the traffic management or cyber‐security targets (such as the number of inspected flows) and operational cost constraints (licence fees, network efficiency or power consumption). In this work, we formulate the vDPI placement problem as a cost minimization problem. The cost captures the different objectives that the operator is pursuing. A placement of vDPIs on the network nodes realizes a trade‐off between these possibly conflicting goals. We cast the problem as a multi‐commodity flow problem and solve it as an integer linear program. We then devise a centrality‐based greedy algorithm and assess its validity by comparing it with the integer linear program optimal solution on a real dataset (GEANT network with 22 nodes and real traffic matrix). We further analyse the scalability of the heuristic by applying it to larger random networks of up to 300 nodes. The results show the network structure and the costs influence time performance. Finally, they demonstrate that the heuristic approximates the optimal on small and medium problem instances well. Copyright © 2015 John Wiley & Sons, Ltd.