Improving the QoE of DASH over SDN: A MCDM Method with an Intelligent Approach

As being one of the most popular applications in the last decade, dynamic adaptive video streaming applications are used by Internet users every day. In such applications, the underlying architecture allows users to change quality adaptively as their request. The purpose of quality or rate adaptation algorithm is to achieve highest QoE possible. In this paper, we propose a rate adaptation algorithm which allows to increase the quality of already buffered video by using Multi-Criteria Decision Making (MCDM) method. Increasing the quality of the buffered video can be beneficial in areas from resiliency to entertainment. We propose to utilize SDN for deciding weights of MCDM method. For this purpose, SDN controller runs a machine learning algorithm by using its knowledge about current network conditions as an input of the learning algorithm. Simulation results show that users achieve higher QoE by using our approach when compared to conventional rate adaptation algorithm.