Joint middlebox selection and routing for software-defined networking

What is it about?

Abstract In the context of Software-Defined Networking (SDN), various sophisticated policy-aware network functions such as intrusion detection, access control and load balancer, can be realized via specified middlebox devices. However, high congestions may occur in specific bottleneck links if middlebox selection and routing are not well jointly planed. To this end, we study a joint optimization of MiddleBox Selection and Routing (MBSR) problem with the objective to maximize the throughput for a specified set of sessions in a SDN network. In order to solve this NP-hard problem, we design a polynomial algorithm using the Markov approximation technique. Numerical results show that the proposed Markov approximation based algorithm outperforms other two benchmark algorithms significantly and generates near-optimal solutions.

Featured Image