Cloning parallel simulations

Abstract

We present a cloning mechanism that enables the evaluation of multiple simulated futures. Performance of the mechanism is analyzed and evaluated experimentally on a shared memory multiprocessor. A running parallel discrete event simulation is dynamically cloned at decision points to explore different execution paths concurrently. In this way what-if and alternative scenario analysis can be performed in applications such as gaming or tactical and strategic battle management. A construct called virtual logical processes avoids repeating common computations among clones and improves efficiency. The advantages of cloning are preserved regardless of the number of clones (or execution paths). Our performance results with a commercial air traffic control simulation demonstrate that cloning can significantly reduce the time required to compute multiple alternate futures.

Enhancing the performance of HLA-based simulation systems via software diversity and active replication

“…Among the solutions oriented to enhancing the performance of simulation systems, a kind of replication approach known as cloning has been proposed in [3,8,9]. The aim of this approach is to allow fast exploration of multiple execution paths due to sharing of portions of the computation on different paths.…”

Alternative Scenario Selection Games for Flood Mitigation Optimization

“…Although there exist many emerging simulation techniques, e.g., simulation cloning [1]~ [6], exact-differential simulation [7], and etc., which in fact provide a feasible way to analyze largescale flood mitigation systems by simulation with various patterns scenarios or parameters, however, there is no guarantee that a simulator could obtain a feasible operation scenario meeting the aforementioned requirements, let alone an optimal one.…”

Distributed simulation of large-scale and detailed models

“…Secondarily, the time required to run such large and complex models is often excessive. Frequently, the amount of time available to obtain the simulation results is very limited, and in some cases faster-than-real-time responses are required (Hybinette and Fujimoto, 2001). …”