Model replication techniques for parameter-influence studies and Monte Carlo simulation with random parameters

  • Authors:

  • Granino A. Korn

  • Affiliations:

  • ECE Department, The University of Arizona, 7750 South Lakeshore Road, No. 15, Chelan, WA 98816, USA

  • Venue:
  • Mathematics and Computers in Simulation
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Modern computers produce large volumes of simulation results so quickly that their management becomes a formidable task. We describe interactive computer software for replicating simulation models with different parameters. A single simulation run then produces results for hundreds of models with different parameter values without the loop overhead imposed by repeated simulations. One can1.arrange corresponding values of model-parameter values and model performance measures in corresponding arrays suitable for use in commercially available spreadsheet and relational-database programs for further processing and archival storage, or 2.produce a Monte Carlo sample of model runs with random parameter values and compute statistics such as various averages or probability estimates as functions of simulation time in a single simulation run.