Time management in the DoD high level architecture
PADS '96 Proceedings of the tenth workshop on Parallel and distributed simulation
Design and implementation of HLA time management in the RTI version F.0
Proceedings of the 29th conference on Winter simulation
Creating computer simulation systems: an introduction to the high level architecture
Creating computer simulation systems: an introduction to the high level architecture
Proceedings of the 32nd conference on Winter simulation
Parallel and Distribution Simulation Systems
Parallel and Distribution Simulation Systems
The Anatomy of the Grid: Enabling Scalable Virtual Organizations
CCGRID '01 Proceedings of the 1st International Symposium on Cluster Computing and the Grid
SOAr-DSGrid: Service-Oriented Architecture for Distributed Simulation on the Grid
Proceedings of the 20th Workshop on Principles of Advanced and Distributed Simulation
DS-RT '08 Proceedings of the 2008 12th IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications
Hi-index | 0.00 |
A Service-Oriented Architecture is essentially a collection of independent services with well-defined interfaces that can be accessed without knowledge of their implementation. The architecture is widely used in Grid computing to achieve resource virtualization, on-demand provisioning, and service (resource) sharing. As the Grid has shown its potential as a suitable environment for simulation and modeling, a Service-Oriented Architecture for Distributed Simulation on the Grid (SOAr-DSGrid) was proposed. Like other simulation systems, time management is a crucial part of the whole system. It manages the logical time and guarantees that the whole simulation system is causally correct. This paper describes the implementation of distributed time management in SOAr-DSGrid. The time management makes use of the simulation topology information to reduce constraints on time advancement between simulation components. Various experiments conducted on a cluster demonstrate that a fully distributed time management system has better scalability and efficiency than the centralized version.