Implementing simulation design of experiments and remote execution on a high performance computing cluster

Abstract

This thesis focused on creating an object-oriented software architecture around which tools can be created to increase the usability of stochastic simulations such as IWARS and Pythagoras on high performance computing clusters. The objective of the architecture was to enable the user to design and execute simulation experiments using a platform-independent client and server to create a common interface for various simulations. The interface input is used to select the experimental factors of interest to the research analyst and then to create the scenario files for each simulation run with minimal human intervention. To develop the architecture the current state of the art was explored, a proposed process flow was developed. This process flow was then vetted by operations researchers from several organizations. A prototype application was developed based on the software architecture. The prototype revealed great benefit in this type of tool.