Evaluation of a Fault-Tolerance Mechanism for HLA-Based Distributed Simulations
2006 (English)In: 20th Workshop on Principles of Advanced and Distributed Simulation, PADS 2006: Singapore; 24 May 2006 through 26 May 2006, 2006, 175-182 p.Conference paper (Refereed)
Successful integration of Modeling and Simulation (M&S) in the future Network-Based Defence (NBD) depends, among other things, on providing fault-tolerant (FT) distributed simulations. This paper describes a framework, named Distributed Resource Management System (DRMS), for robust execution of simulations based on the High Level Architecture. More specifically, a mechanism for FT in simulations synchronized according to the time-warp protocol is presented and evaluated. The results show that utilization of the FT mechanism, in a worst-case scenario, increases the total number of generated messages by 68% if one fault occurs. When the FT mechanism is not utilized, the same scenario shows an increase in total number of generated messages by 90%. Considering the worst-case scenario a plausible requirement on an M&S infrastructure of the NBD, the overhead caused by the FT mechanism is considered acceptable.
Place, publisher, year, edition, pages
2006. 175-182 p.
Computer architecture, Computer simulation, Distributed computer systems, Information management, Network protocols, Resource allocation, Distributed Resource Management System (DRMS), Network-Based Defence (NBD), Time-warp protocols
IdentifiersURN: urn:nbn:se:kth:diva-24253DOI: 10.1109/PADS.2006.18ScopusID: 2-s2.0-33751436352ISBN: 0-7695-2587-3OAI: oai:DiVA.org:kth-24253DiVA: diva2:346035
QC 201008302010-08-302010-08-302010-11-11Bibliographically approved