
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
Alois Ferscha, "Adaptive Time Warp Simulation of Timed Petri Nets," IEEE Transactions on Software Engineering, vol. 25, no. 2, pp. 237257, March/April, 1999.  
BibTex  x  
@article{ 10.1109/32.761448, author = {Alois Ferscha}, title = {Adaptive Time Warp Simulation of Timed Petri Nets}, journal ={IEEE Transactions on Software Engineering}, volume = {25}, number = {2}, issn = {00985589}, year = {1999}, pages = {237257}, doi = {http://doi.ieeecomputersociety.org/10.1109/32.761448}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Software Engineering TI  Adaptive Time Warp Simulation of Timed Petri Nets IS  2 SN  00985589 SP237 EP257 EPD  237257 A1  Alois Ferscha, PY  1999 KW  Adaptive distributed simulation KW  Petri nets KW  Time Warp KW  optimism control KW  CS2 KW  CM5.CR Categories and Subject Descriptors: 1) C.2 (Computer Communication Networks: distributed systems—distributed applications) KW  2) C.4 (Computer Systems Organization: performance of systems—modeling techniques) KW  and 3) I.6.8 (Simulation and Modeling: types of simulation—distributed KW  parallel). VL  25 JA  IEEE Transactions on Software Engineering ER   
Abstract—Time Warp (TW), although generally accepted as a potentially effective parallel and distributed simulation mechanism for timed Petri nets, can reveal deficiencies in certain model domains. Particularly, the unlimited optimism underlying TW 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, an adaptive optimism control mechanism for TW is developed to overcome these shortcomings. By monitoring and statistically analyzing the arrival processes of synchronization messages, TW simulation progress is probabilistically throttled based on the forecasted timestamp of forthcoming messages. Two classes of arrival process characterizations are studied, reflecting that a natural tradeoff exists among the computational and space complexity, and the respective prediction accuracy: While forecasts based on metrics of central tendency are computationally cheap but yield inadequate predictions for correlated arrivals (thus negatively affecting performance), time series based forecast methods give higher prediction accuracy, but at higher computational cost. The sensitivity of the adaptive optimism control with respect to forecast accuracy and computational overhead is analyzed for very large Petri net simulation models executed with the TW protocol on the Meiko CS2 multiprocessor, and for a stress case scenario on the CM5.
Empirical evidence is delivered showing that: 1) probabilistic optimism control, regardless of the communicationcomputation speed ratio of the target execution platform, automatically finds the most appropriate synchronization policy in the spectrum between optimistic TW and conservative Chandy/Misra/Bryant schemes, 2) local control decisions yield an efficient exploitation of simulation model parallelism that is "local" to particular spatial regions, and 3) even if simulation progresses in "phases" of different performance behavior (nonstationary simulations), logical processes can dynamically readjust their synchronization policy, thus in a natural way evading the partitioning problem under imbalanced loads.
[1] H.H. Ammar and S. Deng, "Time Warp Simulation of Stochastic Petri Nets," Proc. Fourth Int'l Workshop Petri Nets and Performance Models, pp. 186195,Los Alamitos, Calif.: IEEE CS Press, 1991.
[2] F. Baccelli and M. Canales, "Parallel Simulation of Stochastic Petri Nets Using Recurrence Equations," ACM Trans. Modeling and Computer Simulation, vol. 3, no. 1, pp. 2041, Jan. 1993.
[3] F. Baccelli, N. Furmento, and B. Gaujal, "Parallel and Distributed Simulation of Free Choice Petri Nets," Proc. Ninth Workshop Parallel and Distributed Simulation (PADS'95), pp. 310, 1995.
[4] D. Ball and S. Hoyt, "The Adaptive TimeWarp Concurrency Control Algorithm," D. Nicol, ed., Proc. SCS Multiconf. Distributed Simulation, pp. 174177,San Diego, Calif., Soc. for Computer Simulation. Simulation Series, vol. 22, no. 1, 1990.
[5] G.E.P. Box and G.M. Jenkins, Time Series Analysis: Forecasting and Control.San Francisco: HoldenDay, 1976.
[6] P.J. Brockwell and R.A. Davis, Time Series: Theory and Methods.New York: SpringerVerlag, 1991.
[7] G. Chiola and A. Ferscha, "Distributed Simulation of Petri Nets," IEEE Parallel and Distributed Technology, vol. 1, no. 3, pp. 3350, Aug. 1993.
[8] G. Chiola and A. Ferscha, "Distributed Simulation of Timed Petri Nets: Exploiting the Net Structure to Obtain Efficiency," M.A. Marsan, ed., Proc. 14th Int'l Conf. Application and Theory of Petri Nets, pp. 146165,Chicago, June 1993, Lecture Notes in Computer Science 691, Berlin: SpringerVerlag, 1993.
[9] M.Q. Cui and St. J. Turner, "A New Approach to the Distributed Simulation of Timed Petri Nets," A. Javor, A. Lehmann, and I. Molnar, eds., Proc. 10th European Simulation Multiconf., pp. 9094. SCS, 1996.
[10] S.R. Das, "Adaptive Protocols for Parallel Discrete Event Simulation," J.M. Charnes, D.J. Morrice, D.T. Brunner, and J.J. Swain, eds., Proc. Winter Simulation Conf., pp. 186193, 1996.
[11] S.R. Das and R.M. Fujimoto, "An Adaptive Memory Management Protocol for Time Warp Parallel Simulation," Proc. ACM Sigmetrics Conf. Measurement and Modeling of Computer Systems, pp. 201210,Nashville, ACM, 1994.
[12] A.P. Dempster, N.M. Laird, and D.B. Rubin, "Maximum Likelihood from Incomplete Data via the EM Algorithm," J.R. Statistical Soc., no. 39, pp. 138, 1977.
[13] A. Ferscha, "Concurrent Execution of Timed Petri Nets," J.D. Tew, S. Manivannan, D.A. Sadowski, and A.F. Seila, eds., Proc. Winter Simulation Conf., pp. 229236, 1994.
[14] A. Ferscha, “Probabilistic Adaptive Direct Optimism Control in Time Warp,” Proc. NInth Workshop Parallel and Distributed Simulation, pp. 120129, 1995.
[15] A. Ferscha, "Parallel and Distributed Simulation of Discrete Event Systems," A.Y. Zomaya, ed., Parallel and Distributed Computing Handbook, pp. 1,0031,041. McGrawHill, 1996.
[16] A. Ferscha, "Optimistic Distributed Execution of Business Process Models," Proc. HICSS31, pp. 723732, IEEE CS Press, 1998.
[17] A. Ferscha and G. Chiola, "SelfAdaptive Logical Processes: The Probabilistic Distributed Simulation Protocol," Proc. 27th Ann. Simulation Symp., pp. 7888.Los Alamitos, Calif.: IEEE CS Press, 1994.
[18] A. Ferscha and J. Luthi, “Estimating Rollback Overhead for Optimism Control in Time Warp,” Proc. 28th Ann. Simulation Symp., pp. 212, 1995.
[19] A. Ferscha and M. Richter, "Massively Parallel Simulation of Business Process Models," A. Javor, A. Lehmann, and I. Molnar, eds., Proc. 10th European Simulation Multiconf., pp. 377381. SCS, 1996.
[20] J. Ferscha, A. Johnson, and St. Turner, "Early Performance Prediction of Parallel Simulation Protocols," Y.M. Teo, W.C. Wong, T.I. Oren, and R. Rimane, eds., Proc. First World Congress Systems Simulation, WCSS'97, pp. 282287,Singapore, IEEE CS Press, Sept. 1997.
[21] R. Fujimoto, “Parallel Discrete Event Simulation,” Comm. ACM, vol. 33, no. 10, pp. 3053, Oct. 1990.
[22] D.O. Hamnes and A. Tripathi, "Investigations in Adaptive Distributed Simulation," D.K. Arvind, R. Bagrodia, and J. YiBing Lin, eds., Proc. Eighth Workshop Parallel and Distributed Simulation (PADS'94), pp. 2023, July 1994.
[23] A.H. Jazwinski, Stochastic Process and Filtering Theory.New York: Academic Press, 1970.
[24] YB. Lin and B.R. Preiss, "Optimal Memory Management for Time Warp Parallel Simulation," ACM Trans. Modeling and Computer Simulation, vol. 1, no. 4, pp. 283307, Oct. 1991.
[25] D. Nicol, "Automated Parallel Simulation of Timed PetriNets," J. Parallel and Distributed Computing, vol. 25, no. 1, pp. 6074, Aug. 1995.
[26] D.M. Nicol and S. Roy, "Parallel Simulation of Timed PetriNets. B. Nelson, D. Kelton, and G. Clark, eds., Proc. Winter Simulation Conf., pp. 574583, 1991.
[27] H. Rajaei, R. Ayani, and L.E. Thorelli, "The Local Time Warp Approach to Parallel Simulation," R. Bagrodia and D. Jefferson, eds., Proc. Seventh Workshop Parallel and Distributed Simulation, pp. 119126,Los Alamitos, Calif.: IEEE CS Press, 1993.
[28] P.F. Reynolds, "A Spectrum of Options for Parallel Simulation," Proc. Winter Simulation Conf., pp. 325332, 1988.
[29] S. Roy, "Massively Parallel SIMD Simulation of Discrete Time Stochastic Petri Nets," J.D. Tew, S. Manivannan, D.A. Sadowski, and A.F. Seila, eds., Proc. Winter Simulation Conf., pp. 229236, 1994.
[30] R.H. Shumway and D.S. Stoffer, "An Approach to Time Series Smoothing and Forecasting Using the EM Algorithm," J. Time Series Analysis, vol. 3, no. 4, pp. 253264, 1982.
[31] G.S. Thomas and J. Zahorjan, "Parallel Simulation of Performance Petri Nets: Extending the Domain of Parallel Simulation," Proc. Winter Simulation Conf., 1991.