Uplink allocation based on user actions for peer-to-peer Video-on-Demand

Abstract

For more than a decade peer-to-peer networking technologies have met with huge success among Internet users, with peer-to-peer traffic already accounting for the largest part of the Internet's total traffic. Peer-to-peer networks have been extensively studied in recent years as an important supporting technology for state-of-the art applications, such as Live Video Streaming and Video-on-Demand. In this work the case of video-on-demand applications over BitTorrent-like unstructured peer-to-peer networks is considered. As a rule, unstructured peer-to-peer networks are pull-based, whereas push-based operation has been associated mostly with structured, tree-based p2p network topologies. While earlier studies maintained the pull-based nature of unstructured networks, recent ones have been investigating the combined use of pull and push operations, aiming at making more efficient use of the available bandwidth. Inspired by such hybrid approaches, this paper proposes a different use for push/pull protocols, uplink allocation based on user actions (i.e. random seek behavior) in video-on-demand applications. In a nutshell, this work proposes the employment of user-triggered push operations to prioritize content pre-fetching for the seemingly more popular parts for the users watching a video, thus increasing replication of such parts across the swarm. © 2014 IEEE.