Experiences with the DEVStone benchmark

  • Authors:
  • Marcelo Gutierrez-Alcaraz;Gabriel Wainer

  • Affiliations:
  • Carleton University, Ottawa, ON, Canada;Carleton University, Ottawa, ON, Canada

  • Venue:
  • Proceedings of the 2008 Spring simulation multiconference
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

DEVS is a formal modeling and simulation (M&S) framework that supports hierarchical, modular model composition. DEVS-based M&S environments have been used successfully to understand, analyze, and develop a variety of systems. As the systems under study become more large and complex, performance of the simulator becomes critical. Nevertheless, evaluating the operation of such simulators is a complex process. We present DEVStone, a synthetic benchmark devoted to automate the evaluation of DEVS-based simulators, which generates models with varied structure and behavior. DEVStone was used to study the efficiency of different simulation engines provided by the CD++ toolkit, this results were later compared with similar results on ADEVS with a demanding set of experiments, enabling thorough performance analysis. DEVStone facilitates performance analysis for successive versions (e.g., upgrades or fixes) of the same simulation engine, and provides a common metric to compare different M&S environments.