Issue No. 02 - February (2009 vol. 20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPDS.2008.67
Zhen Yang , Beijing University of Posts and Telecommunications, Beijing
Huadong Ma , Beijing University of Posts and Telecommunications, Beijing
Today's peer-to-peer (P2P) streaming application periodically suffers from routing hotspots, which are also known as flash crowds. A routing hotspot is typically created by an unanticipated new event that triggers an unanticipated surge of users to request streaming service from some particular peers, temporarily overwhelming the peer's delivery capabilities. In this paper, we propose novel methods that avoid routing hotspots proactively, that is, prior to a congestion event. More specifically, we define an incentive-compatible pricing vector explicitly and show that the hotspot can be avoided if all nodes in the network follow the incentive-compatible pricing policy. In order to apply this mechanism to the P2P streaming distribution applications, we propose an adaptive algorithm for distributed computation of the incentive-compatible pricing vector. The simulation results show that the incentive-compatible pricing mechanism can avoid the routing hotspot effectively.
Hotspot avoiding, game theory, peer-to-peer, streaming service, incentive-compatible.
H. Ma and Z. Yang, "Hotspot Avoidance for P2P Streaming Distribution Application: A Game Theoretic Approach," in IEEE Transactions on Parallel & Distributed Systems, vol. 20, no. , pp. 219-232, 2008.