Publication - A Queueing Theory Based Analysis on Agent Control Mechanisms in Peer-to-Peer based Information Retrieval Systems

Authors: Zhang, Haizheng; Lesser, Victor
Title: A Queueing Theory Based Analysis on Agent Control Mechanisms in Peer-to-Peer based Information Retrieval Systems
Abstract: In cooperative peer-to-peer information retrieval systems, each node can be considered as an intelligent agent and these agents work collectively to provide an information retrieval service. In order to support effectively, multiple, concurrent search sessions in the network, we propose a novel agent control mechanism whose elements include resource selection, local search scheduling, and feedback-based load control. We also introduce a new two-phase query routing algorithm based on this control mechanism. Experimental results show that this framework can reduce congestion situations, increase system throughput, and improve considerably the overall system utility.
Keywords: Farm, Information Retrieval
Publication: International Conference on Information and Knowledge Management 2005 Workshop on Peer to Peer based Information Retrieval
Location: Bremen, Germany
Date: 2005
Sources: HTML: http://www.cs.umass.edu/~hzhang/p2p17-zhang.pdf
Reference: Zhang, Haizheng; Lesser, Victor. A Queueing Theory Based Analysis on Agent Control Mechanisms in Peer-to-Peer based Information Retrieval Systems. International Conference on Information and Knowledge Management 2005 Workshop on Peer to Peer based Information Retrieval . 2005.
bibtex: 
@article{Zhang-401,
  author    = "Haizheng Zhang and Victor Lesser",
  title     = "{A Queueing Theory Based Analysis on Agent Control
               Mechanisms in Peer-to-Peer based Information
               Retrieval Systems}",
  journal   = "International Conference on Information and
               Knowledge Management  2005 Workshop on Peer to
               Peer based Information Retrieval ",
  year      = "2005",
  address   = "Bremen, Germany",
  url       = "http://mas.cs.umass.edu/paper/401",
}