Hierarchical partitioning algorithm for optimistic distributed simulation of DEVS models

https://doi.org/10.1016/S1383-7621(97)00057-XGet rights and content

Abstract

The partitioning problem of models is one of the most important issues which may affect the performance of distributed simulation. This paper presents a novel partitioning algorithm for the optimistic distributed simulation of hierarchical, modular Discrete Event System Specification (DEVS) models. The proposed algorithm pursues the following three goals to achieve the overall objective of the minimum simulation time: (1) to balance the computational loads of partitions, (2) to maximize the parallel execution of independent models, and (3) to minimize inter-processor communication. To maximize parallel execution of independent models, the proposed algorithm utilizes the hierarchical structural information of models available from the hierarchical model design methodology of the DEVS formalism. Through benchmark simulation experiments, we show that the proposed algorithm achieves good performance.

References (37)

  • A.C. Chow et al.

    Abstract simulator for the parallel DEVS formalism

  • A.I. Concepcion

    A hierarchical computer architecture for distributed simulation

    IEEE Transactions on Computers

    (1989)
  • J. Cong et al.

    Acyclic multi way partitioning of boolean networks

  • C.M. Fiduccia et al.

    A linear-time heuristic for improving network partitioning

  • R.M. Fujimoto

    Optimistic approaches to parallel discrete event simulation

    Transactions of the Society for Computer Simulation

    (1990)
  • R.M. Fujimoto

    Parallel discrete event simulation

    Communication ACM

    (1990)
  • D.W. Glazer et al.

    On process migration and load balancing in time warp

    IEEE Transactions on Parallel and Distributed Systems

    (1993)
  • E.K. Haddad

    Partitioned load allocation for minimum parallel processing execution time

  • Cited by (16)

    • The simulation model partitioning problem: An adaptive solution based on self-Clustering

      2017, Simulation Modelling Practice and Theory
      Citation Excerpt :

      Many of the approaches that have been proposed to deal with load balancing are designed to address computational load balancing [24] or the communication aspects [25,26] but not both of them. Moreover, very often, only optimistic synchronization (e.g. the Time-Warp algorithm) is considered [26–28]. In many of the proposed approaches, the granularity of the load balancing mechanism is at the level of the whole LP.

    • Self-reproducible DEVS formalism

      2005, Journal of Parallel and Distributed Computing
    • Internet-Based Adaptive Distributed Simulation of Mobile Ad-hoc Networks

      2019, Proceedings - Winter Simulation Conference
    • Theory of Modeling and Simulation: Discrete Event & Iterative System Computational Foundations

      2018, Theory of Modeling and Simulation: Discrete Event & Iterative System Computational Foundations
    View all citing articles on Scopus
    View full text