2017/01/05 by Stefano D’Aronco, D'Aronco, Stefano, Laura Toni +3
Computer Science · #Image and Video Quality Assessment #Network Traffic and Congestion Control #Peer-to-Peer Network Technologies
paper · pdf · doi:10.48550/arxiv.1701.01392
HTTP adaptive streaming (HAS) has become the universal technology for video\nstreaming over the Internet. Many HAS system designs aim at sharing the network\nbandwidth in a rate-fair manner. However, rate fairness is in general not\nequivalent to quality fairness as different video sequences might have\ndifferent characteristics and resource requirements. In this work, we focus on\nthis limitation and propose a novel controller for HAS clients that is able to\nreach quality fairness while preserving the main characteristics of HAS systems\nand with a limited support from the network devices. In particular, we adopt a\nprice-based mechanism in order to build a controller that maximizes the\naggregate video quality for a set of HAS clients that share a common\nbottleneck. When network resources are scarce, the clients with simple video\nsequences reduce the requested bitrate in favor of users that subscribe to more\ncomplex video sequences, leading to a more efficient network usage. The\nproposed controller has been implemented in a network simulator, and the\nsimulation results demonstrate its ability to share the available bandwidth\namong the HAS users in a quality-fair manner.\n