Dynamic Routing with Online Traffic Estimation for Video Streaming Over Software Defined Networks (SDN)

Abstract

The traffic generated by video streaming applications constitutes a large portion of the Internet traffic over today's networks. Video streaming demands for low latency and high bandwidth. In particular, transmission of high-quality (high-resolution) streaming video may put the network under pressure. Therefore, high-quality video traffic requires network managers to make routing timely and intelligently. SDN provides a global view and centralized control for the whole network which gives opportunities to dynamically manage networks. Meanwhile, machine learning techniques are widely applied in traffic estimation. In this thesis, we use an OpenFlow-based SDN environment and propose a dynamic routing scheme with online traffic estimation to increase the quality of high-quality video streaming and the throughput of the network. The traffic is clustered using an unsupervised machine learning algorithm, and then, the high-quality video traffic flows are rerouted to disjoint paths to relieve the network congestion and have better video quality. The whole design is tested in the Mininet simulator. Simulation results show that the proposed scheme improves the link utilization and reduces the dropped frames caused by delay.