1st International ICST Conference on Bio Inspired Models of Network, Information and Computing Systems

Research Article

Stepwise probabilistic buffering for epidemic information dissemination

  • @INPROCEEDINGS{10.1145/1315843.1315845,
        author={Emrah Ahi and Mine  \`{E}aǧlar and  \O{}znur  \O{}zkasap},
        title={Stepwise probabilistic buffering for epidemic information dissemination},
        proceedings={1st International ICST Conference on Bio Inspired Models of Network, Information and Computing Systems},
        publisher={ACM},
        proceedings_a={BIONETICS},
        year={2006},
        month={12},
        keywords={Buffering epidemic peer-to-peer information dissemination reliability topology-aware.},
        doi={10.1145/1315843.1315845}
    }
    
  • Emrah Ahi
    Mine Çaǧlar
    Öznur Özkasap
    Year: 2006
    Stepwise probabilistic buffering for epidemic information dissemination
    BIONETICS
    ACM
    DOI: 10.1145/1315843.1315845
Emrah Ahi1,*, Mine Çaǧlar2,*, Öznur Özkasap3,*
  • 1: Computational Sciences and Engineering, Koç University, Istanbul, Turkey
  • 2: Department of Mathematics, Koç University, Istanbul, Turkey
  • 3: Department of Computer Engineering, Koç University, Istanbul, Turkey
*Contact email: eahi@ku.edu.tr, mcaglar@ku.edu.tr, oozkasap @ku.edu.tr

Abstract

For large-scale peer-to-peer applications, bio-inspired epidemic protocols have considerable advantages as they are robust against network failures, scalable and provide probabilistic reliability guarantees. While providing reliability, a key issue to consider is the usage of system wide buffer space. In this context, we introduce a novel scheme called stepwise probabilistic buffering that reduces the amount of buffering and distributes the load of buffering to the entire system where every peer does not have the complete view of the system. We compute the performance measures through simulations of large-scale application scenarios.