With the growth of computing power and the proliferation of broadband access to the internet, the use of media streaming has become widely diffused. By using the peer-to-peer (P2P) communication architecture, media streaming can be expected to smoothly react to changes in network conditions and user demands for media streams. In this paper, to achieve continuous and scalable media streaming, we introduce our scalable media search and in-time retrieval methods. Through several simulation experiments, we show that our methods can accomplish continuous media play-out for popular media streams without introducing extra load on the system. However, we also show that an LRU cache replacement algorithm cannot provide users with continuous media play-out for unpopular media streams. To tackle this problem, we take inspiration from biological systems to propose a new cache replacement algorithm that considers the balance between supply and demand for media streams. We demonstrate that our proposed algorithm can improve the continuity of media play-out compared with LRU. Furthermore, we find that the proposed algorithm can adapt to changes in the popularity of various media.
Masahiro Sasabe, Naoki Wakamiya, Masayuki Murata, Hideo Miyahara, Effective Methods for Scalable and Continuous Media Streaming on Peer-to-Peer Networks, European Transactions on Telecommunications, 15(6), pp.549-558, November 2004.
@article{sasabe04EffectiveMethodsScalable,
author = "Sasabe, Masahiro and Wakamiya, Naoki and Murata, Masayuki and Miyahara, Hideo",
title = "Effective {{Methods}} for {{Scalable}} and {{Continuous Media Streaming}} on {{Peer-to-Peer Networks}}",
year = "2004",
month = "November",
journal = "European Transactions on Telecommunications",
volume = "15",
number = "6",
pages = "549--558",
doi = "10.1002/ett.1014"
}