Time Warp Simulation of Timed Petri Nets Sensitivity of Adaptive Methods

Authors:
Alois Ferscha;Michael Richter
Affiliations:
-;-
Venue:
PNPM '97 Proceedings of the 6th International Workshop on Petri Nets and Performance Models
Year:
1997

Citing 9
Cited 0

Investigations in adaptive distributed simulation

PADS '94 Proceedings of the eighth workshop on Parallel and distributed simulation
An adaptive memory management protocol for Time Warp parallel simulation

SIGMETRICS '94 Proceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Concurrent execution of timed Petri nets

WSC '94 Proceedings of the 26th conference on Winter simulation
Parallel and distributed simulation of free choice Petri Nets

PADS '95 Proceedings of the ninth workshop on Parallel and distributed simulation
Probabilistic adaptive direct optimism control in Time Warp

PADS '95 Proceedings of the ninth workshop on Parallel and distributed simulation
Parallel simulation of performance Petri nets: extending the domain of parallel simulation

WSC '91 Proceedings of the 23rd conference on Winter simulation
Parallel simulation of timed Petri-nets

WSC '91 Proceedings of the 23rd conference on Winter simulation
Distributed Simulation of Petri Nets

IEEE Parallel & Distributed Technology: Systems & Technology
Estimating rollback overhead for optimism control in Time Warp

SS '95 Proceedings of the 28th Annual Simulation Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

The unthrottled optimism underlying the Time Warp (TW) parallel simulation protocol can lead to excessive aggressiveness in memory consumption due to saving state histories, and waste of CPU cycles due to overoptimistically progressing simulations that eventually have to be "rolled back". Furthermore, in TW simulations executing in distributed memory environments, the communication overhead induced by the rollback mechanism can cause pathological overall simulation performance. In this work direct optimism control mechanisms are used to overcome these shortcomings by probabilistically controlling simulation progression based on the forecasted time stamp of forthcoming messages. Several forecast methods are presented and their performance is compared for very large Petri net simulation models executed with the TW protocol on the Meiko CS-2.