Ant colony optimization for QoE-centric flow routing in software-defined networks

We present design, implementation, and an evaluation of an ant colony optimization (ACO) approach to flow routing in software-defined networking (SDN) environments. While exploiting a global network view and configuration flexibility provided by SDN, the approach also utilizes quality of experience (QoE) estimation models and seeks to maximize the user QoE for multimedia services. As network metrics (e.g., packet loss) influence QoE for such services differently, based on the service type and its integral media flows, the goal of our ACO-based heuristic algorithm is to calculate QoE-aware paths that conform to traffic demands and network limitations. A Java implementation of the algorithm is integrated into SDN controller OpenDaylight so as to program the path selections. The evaluation results indicate promising QoE improvements of our approach over shortest path routing, as well as low running time.