Uncertainty Quantification for Parallel Discrete Event Simulation

• Activity Number: 36 - Statistcal Theory and Uncertainty Quantification in Physical Sciences
• Type: Contributed
• Date/Time: Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Section on Physical and Engineering Sciences
• Author(s): Kevin Quinlan* and Jim Leek and Charles Tong and Joshua Sherfield
• Companies: Lawrence Livermore National Laboratory and Lawrence Livermore National Laboratory and Lawrence Livermore National Laboratory and Lawrence Livermore National Laboratory
• Keywords: Discrete Event Simulation; Agent Based Models; Uncertainty Quantification

Abstract

Parallel Discrete Event Simulation (PDES) is a useful framework for agent-based models (ABM) and other systems where complex interactions occur. These simulations mimic the operation of a real or proposed system, such as the day-to-day operation of the stock market, the running of an assembly line in a factory, or the interactions on computer networks. PDES may act in non-contiguous and non-linear manners, making traditional response surfaces difficult to use. PDES often include a large amount of stochasticity, which generates heteroscedastic error in the quantities of interest. Often the simulation models a large number of agents with multiple parameter settings each, but the agents may also fall into homogeneous classes. Considering these many challenges, we present methodology related to the design and analysis of PDES for multiple applications.

LLNL-ABS-766659 This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.