CaltechAUTHORS
  A Caltech Library Service

Advanced Message Routing for Scalable Distributed Simulations

Barrett, Brian and Gottschalk, Thomas (2004) Advanced Message Routing for Scalable Distributed Simulations. In: The Interservice/Industry Training, Simulation and Education Conference (I/ITSEC), 6-9 December, 2004, Orlando, FL. (Submitted) https://resolver.caltech.edu/CaltechCACR:2004.216

[img]
Preview
PDF
See Usage Policy.

370kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechCACR:2004.216

Abstract

The Joint Forces Command (JFCOM) Experimentation Directorate (J9)'s recent Joint Urban Operations (JUO) experiments have demonstrated the viability of Forces Modeling and Simulation in a distributed environment. The JSAF application suite, combined with the RTI-s communications system, provides the ability to run distributed simulations with sites located across the United States, from Norfolk, Virginia to Maui, Hawaii. Interest-aware routers are essential for communications in the large, distributed environments, and the current RTI-s framework provides such routers connected in a straightforward tree topology. This approach is successful for small to medium sized simulations, but faces a number of significant limitations for very large simulations over high-latency, wide area networks. In particular, traffic is forced through a single site, drastically increasing distances messages must travel to sites not near the top of the tree. Aggregate bandwidth is limited to the bandwidth of the site hosting the top router, and failures in the upper levels of the router tree can result in widespread communications losses throughout the system. To resolve these issues, this work extends the RTI-s software router infrastructure to accommodate more sophisticated, general router topologies, including both the existing tree framework and a new generalization of the fully connected mesh topologies used in the SF Express ModSAF simulations of 100K fully interacting vehicles. The new software router objects incorporate the scalable features of the SF Express design, while optionally using low-level RTI-s objects to perform actual site-to-site communications. The (substantial) limitations of the original mesh router formalism have been eliminated, allowing fully dynamic operations. The mesh topology capabilities allow aggregate bandwidth and site-to-site latencies to match actual network performance. The heavy resource load at the root node can now be distributed across routers at the participating sites.


Item Type:Conference or Workshop Item (Paper)
Group:Center for Advanced Computing Research
Record Number:CaltechCACR:2004.216
Persistent URL:https://resolver.caltech.edu/CaltechCACR:2004.216
Usage Policy:You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.
ID Code:28200
Collection:CaltechCACR
Deposited By: Imported from CaltechCACR
Deposited On:01 Dec 2004
Last Modified:03 Oct 2019 03:30

Repository Staff Only: item control page