1st International ICST Conference on Networks for Grid Applications

Research Article

A Peer-to-Peer Meta-Scheduler for Service-Oriented Grid Environments

Download552 downloads
  • @INPROCEEDINGS{10.4108/gridnets.2007.2164,
        author={Kay Dornemann and Jorg Prenzer and Bernd Freislebe},
        title={A Peer-to-Peer Meta-Scheduler for Service-Oriented Grid Environments},
        proceedings={1st International ICST Conference on Networks for Grid Applications},
        publisher={ICST},
        proceedings_a={GRIDNETS},
        year={2007},
        month={10},
        keywords={meta-scheduling Grid computing peer-to-peer computing ant colonies},
        doi={10.4108/gridnets.2007.2164}
    }
    
  • Kay Dornemann
    Jorg Prenzer
    Bernd Freislebe
    Year: 2007
    A Peer-to-Peer Meta-Scheduler for Service-Oriented Grid Environments
    GRIDNETS
    ICST
    DOI: 10.4108/gridnets.2007.2164
Kay Dornemann1,*, Jorg Prenzer1,*, Bernd Freislebe1,*
  • 1: Department of Mathematics and Computer Science, University of Marburg Hans-Meerwein-Str. 3, D-35032 Marburg, Germany
*Contact email: doernemk@informatik.uni-marburg.de, prenzerj@informatik.uni-marburg.de, freisleb@informatik.uni-marburg.de

Abstract

Meta-scheduling in a Grid is aimed at enabling the efficient sharing of computing resources managed by different local schedulers within a single organization or scattered across several administrative domains. Since current Grid metaschedulers operate in a centralized fashion and thus are single points of failure, we present a distributed meta-scheduler for a service-oriented Grid environment based on peer-to-peer (P2P) networking techniques and ant colony optimization algorithms adapted to a P2P network. In the proposed approach, the meta-scheduling process provides automatic load balancing, is completely decentralized, fault tolerant, scalable, and does not require complex administration. Experimental results demonstrate that scheduling decisions are made quickly and lead to a good balance of the computational load.