Date of Award

Spring 2007

Document Type


Degree Name

Doctor of Philosophy (PhD)


Electrical & Computer Engineering

Committee Director

James F. Leathrum, Jr.

Committee Member

Roland Mielke

Committee Member

Lee A. Belfore II

Committee Member

C. Michael Overstreet


The Distributed, Independent-Platform, Event-Driven Simulation Engine Library (DIESEL) is a simulation executive, capable of supporting both sequential and distributed discrete-event simulations. A system level specification is provided along with the expected behavior of each component within DIESEL. This behavioral specification of each component, along with the interconnection and interaction between the different components, provides a complete description of the DIESEL behavioral model. The model provides a considerable amount of freedom for an application developer to partition the simulation model, when building sequential and distributed applications with respect to balancing the number of events generated across different components. It also allows a developer to modify underlying algorithms in the simulation executive, while causing no changes to the overall system behavior so long as the algorithms meet the behavioral specifications.

The behavioral model is object-oriented and developed using a hierarchical approach. The model is not targeted towards any programming language or hardware platform for implementation. The behavioral specification provides no specifics about how the model should be implemented. A complete and stable implementation of the behavioral model is provided as a proof-of-concept, and can be used to develop commercial applications. New and independent implementations of the complete model can be developed to support specific commercial and research efforts. Specific components of the model can also be implemented by students in an educational environment, using strategies different from the ones used within the current implementation. DIESEL provides a research environment for studying different aspects of Parallel Discrete-Event Simulation, such as event management strategies, synchronization algorithms, communication mechanisms, and simulation state capture capabilities.