Dynamic resolution in distributed cyber-physical system simulation
Proceedings of the 2013 ACM SIGSIM conference on Principles of advanced discrete simulation
| Hi-index | 0.00 |
This paper investigates time management for distributedsimulations in active networks.Time management is essentially the computation of the Lower Bound Time Stamp(LBTS) across federates in a distributed simulation, includingin-transit (in-flight) messages.We show that the LBTScomputation is an instance of the Distributed TerminationDetection (DTD) problem and how DTD algorithms can beapplied to LBTS in an active network.These algorithmsare potentially much more efficient than traditional LBTSalgorithms that rely on point-to-point communication.Weintroduce the Distinguished Root Node algorithm that cancompute LBTS in O(log n) time in general network topologiesusing a prototype implemented in Java.Experimentalresults are reported for the Active Time Management Daemonprototype implementation in (1) a simple testbed configuration,(2) a larger cluster environment, (3) an ns-2 simulationof very large configurations, and (4) integrated intoan actual HLA-compliant run-time and simulation.Whileactive network algorithms have the potential for improvedfunctionality and superior performance, this potential willonly be fully realized when "native" implementations arepossible.For wide-scale deployment, real-world issues such as reliable delivery, dynamic routing topologies, security and fault tolerance will have to be systematically ad-dressed.Also, in the area of distributed computing known as grid computing, the management of distributed resources is a key issue. Hence, we plan to use the grid computing infrastructureto manage overlays and facilitate the use of activenetworks by large-scale, distributed grid applications.