A Game Theoretical Framework for Token-Based Adaptive Video Streaming

We consider a multi-stage Bayesian game to model the interaction between an adaptive video streaming client and a congested network adopting a token-based policy for QoS provisioning. The Bayesian type of the network is its level of congestion, which is initially unknown to the client but heavily influences its payoff, so that the client may be interested in estimating it. Thus, we consider the Bayesian Nash equilibrium of the stage game and also we evaluate an iterative estimation process performed by the client throughout the stages, which allow to tune its equilibrium action. We discuss how the initial conditions can gauge the convergence speed of the estimate. We find out that, while the network type may be sometimes hard to evaluate, especially in low congestion scenarios, nevertheless the equilibrium action of the client is still very close to the ideal best response with full knowledge of the network type. We extend this result to the ability of the client to correctly estimate the prior distribution of the network type from multi-stage streaming games.