Joint virtual network function selection and traffic steering in telecom networks

© 2017 IEEE. Following the trend of Network Function Virtualization (NFV), telecom operators widely deploy diverse types of Virtual Network Functions (VNF) (such as firewall, load balancer, and proxy, etc.) on specified software-defined middlebox at various network locations. Traffic needs to go through the desired VNFs according to pre-defined policies, which forms a Service Function Chain (SFC). However, how to maximize traffic throughput with end-to-end latency guaranteed when steering SFC requests is still an open problem. To this end, we study a joint optimization of VNF selection and traffic steering problem in telecom networks. Firstly, we formulate this problem as an Integer Linear Programming (ILP) model. Then, we design an efficient heuristic algorithm based on dynamic programming. Extensive simulation results show that compared with the previous algorithms, our algorithm can increase 30.86% throughput of SFC requests while guaranteeing end-to-end latency requirement.