Small-World Overlay P 2 P Networks : Construction and Handling Dynamic Flash Crowd

In this paper, we consider how to “construct” and “maintain” an overlay structured P2P network based on the “smallworld paradigm”. Two main attractive properties of a smallworld network are (1) low average hop distance between any two randomly chosen nodes and, (2) high clustering coefficient. A network with a low average hop distance implies a small latency for object lookup. While a network with a high clustering coefficient implies the underlying P2P network has the “potential” to provide object lookup service even in the midst of heavy object traffic loading, for example, under a flash crowd scenario. In this paper, we present the SWOP protocol of constructing a small-world overlay P2P network. We compare our result with other structured P2P networks such as the Chord protocol. Although the Chord protocol can provide object lookup with latency of complexity, where is the number of nodes in a P2P network, we show that the SWOP protocol can further improve the object lookup performance. We also take advantage of the high clustering coefficient of a small-world P2P network and propose an object replication algorithm to handle the heavy object traffic loading situation, e.g. under the dynamic flash crowd scenario. We show that the SWOP network can quickly and efficiently deliver the “popular” and “dynamic” object to all requested nodes. Based on our knowledge, this is the first work that addresses how to handle the “dynamic” flash crowd scenario on a structured P2P

[1]  Emanuel Parzen,et al.  Stochastic Processes , 1962 .

[2]  Sharon L. Milgram,et al.  The Small World Problem , 1967 .

[3]  Gregory K. Miller,et al.  Elements of Applied Stochastic Processes , 1972 .

[4]  M. Weigt,et al.  On the properties of small-world network models , 1999, cond-mat/9903411.

[5]  Ian Clarke,et al.  Freenet: A Distributed Anonymous Information Storage and Retrieval System , 2000, Workshop on Design Issues in Anonymity and Unobservability.

[6]  Jon M. Kleinberg,et al.  Navigation in a small world , 2000, Nature.

[7]  Jon M. Kleinberg,et al.  The small-world phenomenon: an algorithmic perspective , 2000, STOC '00.

[8]  Peter Druschel,et al.  Pastry: Scalable, distributed object location and routing for large-scale peer-to- , 2001 .

[9]  D. Watts,et al.  Small Worlds: The Dynamics of Networks between Order and Randomness , 2001 .

[10]  David R. Karger,et al.  Chord: A scalable peer-to-peer lookup service for internet applications , 2001, SIGCOMM '01.

[11]  Moni Naor,et al.  Viceroy: a scalable and dynamic emulation of the butterfly , 2002, PODC '02.

[12]  M. Newman,et al.  Percolation and epidemics in a two-dimensional small world. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  Margarida Mitjana,et al.  Broadcasting in Small-world Communication Networks , 2002, SIROCCO.

[14]  Ramesh Govindan,et al.  Using the small-world model to improve Freenet performance , 2002, Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.

[15]  Ian T. Foster,et al.  Locating Data in (Small-World?) Peer-to-Peer Scientific Collaborations , 2002, IPTPS.

[16]  Dan Rubenstein,et al.  A lightweight, robust P2P system to handle flash crowds , 2002, IEEE Journal on Selected Areas in Communications.

[17]  Abhishek Kumar,et al.  Ulysses: a robust, low-diameter, low-latency peer-to-peer network , 2004, Eur. Trans. Telecommun..

[18]  Ellen W. Zegura,et al.  Adding structure to unstructured peer-to-peer networks: the use of small-world graphs , 2005, J. Parallel Distributed Comput..

[19]  Sambit Sahu,et al.  An Analysis of a Simple P2P Protocol for Flash Crowd Document Retrieval , 2007 .