Flash Crowd Absorber for P2P Video Streaming

Abstract

This paper proposes a method to absorb flash crowd in P2P video streaming systems. The idea of the proposed method is to reduce the time before a newly arrived node becoming an uploader by explicitly constructing a group of newly arrived nodes called flash crowd absorber (FCA). FCA grows continuously while serving a video stream to the members of the group, and it is explicitly controlled so that the upload capacity of the nodes is fully utilized and it attains a nearly optimal latency of the stream during a flash crowd. A numerical comparison with a naive treebased scheme is also given.

A Node Virtualization Scheme for Structured Overlay Networks Based on Multiple Different Time Intervals

“…In overlay networks, virtual node techniques have been researched in order to avoid load concentration into the specific physical node [25,26]. In [25,26], Shao et al also assume "flash crowd" where many requests are concentrated to the specific service in a short time [27]. The load-concentrated node asks low-load nodes for help.…”

Semi-Structured BitTorrent Protocol with Application to Efficient P2P Video Streaming

“…In addition, if peers in a clique directly receive piece streams from seeders, peers in the clique can forward acquired pieces to the successor in the clique chain. Thus as long as the arrival timing of joining peers is not concentrated on a short time period, we could realize a smooth flow of streams along the clique chain (if it occurs a kind of flash crowd, we could take another approach such as [8]).…”

Peer-to-Peer Video Streaming of Non-Uniform Bitrate with Guaranteed Delivery Hops

“…In this paper, we assume that each video stream has its own quality level encoded with a constant bitrate * * * * * , and consider the problem of delivering those video streams to their subscribers with as small server cost as possible while keeping the performance of video streaming in terms of the throughput and the latency. If a simple tree-structured overlay is used for delivering each video stream, which will be referred to as a naive scheme hereafter, subscribers of high quality video stream are easily overloaded, and it limits the number of participants which allows the delivery with a designated latency and a server cost [1], [12], [13]. In general, to attain a low latency in P2P video streaming, we should bound the number of intermediate peers encountered during the delivery of video streams, but it is difficult for high quality video streams since it occupies a large portion of the upload capacity of the participant which severely limits the number of peers which could directly receive a stream from intermediate peers (e.g., each peer can forward a received video stream to at most one peer if the bitrate of the stream exceeds a half of the upload capacity of the peer).…”