Abstract
This article presents a framework for distributed simulation that is based on system-theoretic and logical-process concepts. The framework describes a three-part worldview for developing simulation models. These are modeling formalisms, abstract simulators, and computational environments. A unified view of time and causality allows for the application of system-theoretic notions of causality within a distributed simulation environment. Within this framework, the authors introduce a unified notion of causality for use in parallel simulations. Furthermore, they describe an approach for developing distributed simulation models that evolve from modeling constructs to simulation algorithms and their implementations. The framework is exemplified using the discrete event system specification (DEVS) modeling formalism, its abstract simulator, and a parallel algorithm that implements the abstract simulator.
Original language | English |
---|---|
Pages (from-to) | 577-589 |
Number of pages | 13 |
Journal | SIMULATION |
Volume | 80 |
Issue number | 11 |
DOIs | |
State | Published - Nov 2004 |
Externally published | Yes |
Keywords
- Causality
- DEVS
- Distributed
- Logical process
- System theory
- Time