Cooperative Caching for Peer-to-Peer On-Demand Streaming

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering

FYT Presentation and Demonstration

Title: "Cooperative Caching for Peer-to-Peer On-Demand Streaming"

by

Mr. YANG, Yang

In peer-to-peer (P2P) video-on-demand (VoD) streaming applications, 
multimedia content is divided into segments and peers can seek any 
segments for viewing at any stime. Since different segments may be of 
different popularity, random segment caching would lead to segment 
popularity-supply mismatch, and hence uneven workload distribution among 
peers. Furthermore, popular segments may be far from peers, leading to 
inefficient search and streaming. In this paper, we study optimal segment 
caching for P2P on-demand streaming.

In P2PVoD, peers cooperate in a distributed manner to cache and search 
for segments. We first formulate the cooperative caching (CC) problem, 
which is to cache segments so as to minimize end-to-end delay given peer 
bandwidth and capacity. The problem is a zero-one integer programming, and 
is shown to be NP-hard. We then propose a distributed caching algorithm in 
which each peer adaptively caches and replaces segments to minimize the 
popularity-supply discrepancy while achieving low segment distance from 
peers. We also adopt a segment lookup technique which proactively 
advertises updated segment availability in a scalable manner to provide 
near instant segment search. Through simulations we show that our scheme 
achieves low average end-to-end delay. The segment lookup technique 
achieves low overhead and search latency, and high hit rate of finding 
segments in the presence of peer churn.

Date		: 	April 26, 2010

Time		:	5:30pm - 6:15pm

Venue		:	3416

Advisor		:	Dr. Gary Chan

2nd Reader	:	Dr. Lin Gu