Delay and Cost Aware Adaptive Deployment and Migration of Service Function Chains in 5G

Abstract

With the increasing demand of 5G network applications, efficient placement of virtual network functions (VNFs) of the service function chaining (SFC) is a crucial problem to address for providing real-time services at reduced deployment costs. However, limited effort has been made in the literature works to jointly minimize resource usage cost and service delay in the 5G network through migration of VNFs when and where it is required. In this paper, we have developed an optimization framework for VNF placement of SFC requests, which brings a trade-off between the aforementioned two objectives. The developed framework is a multi-objective linear programming (MOLP) problem that takes into consideration the dynamic pricing scheme of the resources and user application demands. The experimental findings demonstrate that the proposed system outperforms state-of-the-art approaches in terms of service latency and resource usage costs as high as 10% and 15%, respectively.