Distributed Discrete-Event Simulation

Distributed Discrete-Event Simulation

Vol. 18, No. 1, March 1986 | JAYADEV MISRA
The paper introduces a novel approach to system simulation, addressing the limitations of traditional sequential discrete-event simulations, which are often limited by the number of events they can handle. It proposes distributed discrete-event simulation, which leverages multiple processors to partition the simulation, potentially improving performance. The basic distributed simulation scheme, which uses time encoding, is described, but it faces the challenge of deadlock. Several techniques for deadlock avoidance and detection are discussed. The paper focuses on the theoretical aspects of distributed discrete-event simulation, aiming to provide a foundation for future research and practical applications. The authors argue that distributed simulation offers a promising solution for speeding up simulations, especially for complex systems like telephone switches and computer networks. They highlight the need for further empirical studies to validate the performance gains and explore various heuristics for deadlock resolution. The paper also includes examples to illustrate the concepts and provides a detailed algorithm for distributed simulation.The paper introduces a novel approach to system simulation, addressing the limitations of traditional sequential discrete-event simulations, which are often limited by the number of events they can handle. It proposes distributed discrete-event simulation, which leverages multiple processors to partition the simulation, potentially improving performance. The basic distributed simulation scheme, which uses time encoding, is described, but it faces the challenge of deadlock. Several techniques for deadlock avoidance and detection are discussed. The paper focuses on the theoretical aspects of distributed discrete-event simulation, aiming to provide a foundation for future research and practical applications. The authors argue that distributed simulation offers a promising solution for speeding up simulations, especially for complex systems like telephone switches and computer networks. They highlight the need for further empirical studies to validate the performance gains and explore various heuristics for deadlock resolution. The paper also includes examples to illustrate the concepts and provides a detailed algorithm for distributed simulation.
Reach us at info@study.space