Joint transmission scheduling and congestion control for adaptive streaming in wireless device-to-device networks

We consider the jointly optimal design of a transmission scheduling and admission control policy for adaptive streaming over wireless device-to-device networks. We formulate the problem as a dynamic network utility maximization and observe that it naturally decomposes into two subproblems: admission control and transmission scheduling. The resulting algorithms are simple and suitable for distributed implementation. The admission control decisions involve each user choosing the quality of the video chunk asked for download, based on the network congestion in its neighborhood. This form of admission control is compatible with the current video streaming technology based on the DASH protocol over TCP connections. We also consider a mechanism for dropping bits from the transmission queues in order to obtain deterministic bounds on the queueing delays, which determine the number of video chunks that should be pre-fetched in order to guarantee smooth playback without interruptions.