Joint middlebox selection and routing for software-defined networking

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 traffic 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 an 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 benchmark algorithms significantly and generates near-optimal solutions.