2019/10/04 by Kyoomars Alizadeh Noghani, Noghani, Kyoomars Alizadeh, Andreas Kassler +3
Computer Science · Engineering · #Advanced Optical Network Technologies #FOS: Computer and information sciences #Network Traffic and Congestion Control #Networking and Internet Architecture (cs.NI) #Software-Defined Networks and 5G
paper · pdf · doi:10.48550/arxiv.1910.01881
openalex publication_date 2019/10/04 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Optimal placement of Virtual Network Functions (VNFs) in virtualized data\ncenters enhances the overall performance of Service Function Chains (SFCs) and\ndecreases the operational costs for mobile network operators. Maintaining an\noptimal placement of VNFs under changing load requires a dynamic\nreconfiguration that includes adding or removing VNF instances, changing the\nresource allocation of VNFs, and re-routing corresponding service flows.\nHowever, such reconfiguration may lead to notable service disruptions and\nimpose additional overhead on the VNF infrastructure, especially when\nreconfiguration entails state or VNF migration. On the other hand, not changing\nthe existing placement may lead to high operational costs. In this paper, we\ninvestigate the trade-off between the reconfiguration of SFCs and the\noptimality of the resulting placement and service flow (re)routing. We model\ndifferent reconfiguration costs related to the migration of stateful VNFs and\nsolve a joint optimization problem that aims to minimize both the total cost of\nthe VNF placement and the reconfiguration cost necessary for repairing a\nsuboptimal placement. Numerical results show that a small number of\nreconfiguration operations can significantly reduce the operational cost of the\nVNF infrastructure; however, too much reconfiguration may not pay off should\nheavy costs be involved.\n