Modelling and simulation-based design of a distributed devs simulator

Authors:
Eugene Syriani;Hans Vangheluwe;Amr Al Mallah
Affiliations:
University of Alabama, Tuscaloosa, AL;University of Antwerp, Antwerp, Belgium;McGill University, Montréal, Canada
Venue:
Proceedings of the Winter Simulation Conference
Year:
2011

Citing 6
Cited 0

Multifacetted modelling and discrete event simulation

Multifacetted modelling and discrete event simulation
Parallel DEVS: a parallel, hierarchical, modular modeling formalism and its distributed simulator

Transactions of the Society for Computer Simulation International
Distributed simulation of hierarchical DEVS models: hierarchical scheduling locally and time warp globally

Transactions of the Society for Computer Simulation International
DEVS Peer-to-Peer Protocol for Distributed and Parallel Simulation of Hierarchical and Decomposable DEVS Models

ISITC '07 Proceedings of the 2007 International Symposium on Information Technology Convergence
Programmed Graph Rewriting with Time for Simulation-Based Design

ICMT '08 Proceedings of the 1st international conference on Theory and Practice of Model Transformations
Design of A QoS-Aware Service Composition and Management System in Peer-to-Peer Network Aided by DEVS

DS-RT '08 Proceedings of the 2008 12th IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Distributed, discrete-event simulators are typically deployed on different computing and network platforms using different implementation languages. This hampers realistic performance comparisons between simulator implementations. Furthermore, algorithms used are typically only present in code rather than explicitly modeled. This prohibits rigorous analysis and re-use. In this paper, the structure and behavior of a distributed simulator for the DEVS formalism is modeled explicitly, in the DEVS formalism. Simulation of this model of the simulator allows for the quantitative analysis of reliability and performance of different alternative simulator designs. In particular, using a model of a distributed simulator allows one to simulate scenarios such as failures of computational and network resources, which can be hard to realize in reality. We demonstrate our model-based approach by modeling, simulating and ultimately synthesizing a distributed DEVS simulator. Our goal is to achieve fault tolerance whilst optimizing performance.