Understanding overlay characteristics of a large-scale peer-to-peer IPTV system

Abstract

This paper presents results from our measurement and modeling efforts on the large-scale peerto-peer (p2p) overlay graphs spanned by the PPLive system, the most popular and largest p2p IPTV (Internet Protocol Television) system today. Unlike other previous studies on PPLive, which focused on either network-centric or user-centric measurements of the system, our study is unique in (a) focusing on PPLive overlay-specific characteristics, and (b) being the first to derive mathematical models for its distributions of node degree, session length, and peer participation in simultaneous overlays.Our studies reveal characteristics of multimedia streaming p2p overlays that are markedly different from existing file-sharing p2p overlays. Specifically, we find that: (1) PPLive overlays are similar to random graphs in structure and thus more robust and resilient to the massive failure of nodes, (2) Average degree of a peer in the overlay is independent of the channel population size and the node degree distribution can be fitted by a piecewise function, (3) The availability correlation between PPLive peer pairs is bimodal, i.e., some pairs have highly correlated availability, while others have no correlation, (4) Unlike p2p file-sharing peers, PPLive peers are impatient and session lengths (discretized, per channel) are typically geometrically distributed, (5) Channel population size is time-sensitive, self-repeated, event-dependent, and varies more than in p2p filesharing networks, (6) Peering relationships are slightly locality-aware, and (7) Peer participation in simultaneous overlays follows a Zipf distribution. We believe that our findings can be used to understand current large-scale p2p streaming systems for future planning of resource usage, and to provide useful and practical hints for future design of large-scale p2p streaming systems.

TRANSIT: Supporting transitions in Peer-to-Peer live video streaming

“…1) Trace-based Workload: The traces used in this work were collected by Vu et al [23] in a measurement study of PPLIVE and are provided in the P2P trace archive [27]. The characteristics of the traces closely resemble traces used in earlier studies by Hei et al [6] and have also been the basis of a recent study by Hu et al [7].…”

“…The distribution of session lengths is derived from the aforementioned measurement trace [23]. After time t fc the number of online peers is increased linearly up to m fc · |P | max .…”

“…Both situations occur in real-life systems as well, for example on New Year's Eve [6] or after unforeseen events such as earthquakes [23], of course depending on the content the video stream is offering. The flash-crowd workload captures these extremes, thus providing a realistic scenario to evaluate the benefits of a transition-enabled approach in such a situation.…”

Large-scale measurement experiments of P2P-TV systems insights on fairness and locality

“…In their works, Hei. et al [32] and Vu et al [33] modified a PPLive client to crawl the PPLive network. Vu et al [33] indicate that the PPLive overlay characteristics differ from those of P2P file-sharing.…”

“…et al [32] and Vu et al [33] modified a PPLive client to crawl the PPLive network. Vu et al [33] indicate that the PPLive overlay characteristics differ from those of P2P file-sharing. They show that PPLive network is similar to random graphs and thus more resilient to the massive failure of nodes.…”