Efficient Virtual Network Function Placement for Poisson Arrived Traffic

摘要

Network Function Virtualization (NFV) and Software Defined Network have revolutionized data networks. For deployment of the VNFs, it is imperative to consider the queuing delay occurring in the NFV servers. The presented work suggests to incorporate the Poisson distribution of packet arrival rate and packet size along with the limited processing capacity of NFV server. The underlying phenomenon is framed as a 0-1 fractional programming problem. More precisely, the underlying problem is framed to 0-1 MILP to get the optimal solution. Since the VNF placement problem is NP-hard, therefore, we propose two heuristic algorithms to get the solution. Extensive simulations demonstrate that our algorithms effectively reduce 72.9% delay compared with the universal algorithm Improve Service Chaining Performance (ISCP).