Characterizing adaptive video streaming control systems

Abstract

Adaptive video streaming systems aim at providing the best user experience given the user device and the network available bandwidth. To the purpose, a controller selecting the video bitrate from a discrete set ℒ has to be designed. The control goal is to maximize the video bitrate while avoiding playback interruptions and minimizing video bitrate switches. In the literature two different approaches, which we name rate-based actuation and level-based actuation, have been explored. The first one adapts both the received rate and the video bitrate, whereas the second acts only on the video bitrate. In this paper we advocate the adoption of level-based actuation controllers and we propose a hybrid dynamical system that models the essential features of such a class of controllers. With this model we are able to derive the minimum obtainable video bitrate switching frequency which can be considered as a benchmark for any level-based actuation controller. Finally, we show how to design the video level set ℒ to obtain a performance trade-off between switching frequency and storage cost requirements at the servers. The theoretical results are validated through numerical simulation and experimental evaluation.