A two-stage approach for multicast-oriented virtual network function placement

Abstract Network function virtualization (NFV) is an emerging network paradigm that decouples softwarized network functions from proprietary hardware. Nowadays, resource allocation has become one of the hot topics in the NFV domain. In this paper, we formulate a service function chain (SFC) mapping problem in the context of multicast, which is also referred to as the multicast-oriented virtual network function placement (MVNFP) problem. The objective function considers end-to-end delay as well as compute resource consumption, with bandwidth requirements met. A two-stage approach is proposed to address this problem. In the first stage, Dijkstra’s algorithm is adopted to construct a multicast tree. In the second stage, a novel estimation of distribution algorithm (nEDA) is developed to map a given SFC over the multicast tree. Simulation results show that the proposed two-stage approach outperforms a number of state-of-the-art evolutionary, approximation, and heuristic algorithms, in terms of the solution quality.