HiPUTS: Super-Scalable Simulation of Microscopic Continuous Urban Traffic Model
DOI:
https://doi.org/10.26034/lu.akwi.2026.8849Schlagworte:
HPC, Simulation, Urban traffic, Scalability, Multi-agent systemsAbstract
The presented HiPUTS system is a new urban traffic simulator, which aims at providing (almost) linear scalability of the distributed simulation computation up to several thousand computing cores of a modern supercomputer. The simulation system supports microscopic, continuous traffic models with fully transparent distribution of computations which does not affect simulation results. In this paper we present the architecture and crucial algorithms of the simulation system and evaluate its performance and scalability. The synthetic scalability evaluation includes both strong and weak scaling experiments. The paper is summarized with a set of design guidelines, which are important for obtaining super-scalability of distributed spatial simulations.
Literaturhinweise
A. Acosta, J. Espinosa, and J. Espinosa. Distributed simulation in sumo revisited: Strategies for network partitioning and border edges management. In Proceedings of the 4th SUMO User Conference, pages 61–71, 2016.
M. Ahmed, R. Seraj, and S.M.S. Islam. The k-means algorithm: A comprehensive survey and performance evaluation. Electronics, 9(8):1295, 2020.
G.M Amdahl. Validity of the single processor approach to achieving large scale computing capabilities. In Proceedings of the April 18-20, 1967, spring joint computer conference, pages 483–485, 1967.
N. Arroyo, A. Acosta, J. Espinosa, and J. Espinosa. A new strategy for synchronizing traffic flow on a distributed simulation using sumo. EPiC series in engineering, 2:152–161, 2018.
H. Chen, K. Yang, S.G. Rizzo, G. Vantini, P. Taylor, X. Ma, and S. Chawla. Qarsumo: a parallel, congestion-optimized traffic simulator. In Proceedings of the 28th International Conference on Advances in Geographic Information Systems, pages 578–588, 2020.
C. Dobler. Implementation of a time step based parallel queue simulation in matsim. In 10th Swiss Transport Research Conference. Ascona, 2010.
C. Engelmann and A. Geist. Super-scalable algorithms for computing on 100,000 processors. In International Conference on Computational Science, pages 313–321. Springer, 2005.
D.L. Gerlough. Simulation of Freeway Traffic on a General-purpose Discrete Variable Computer. University of California, Los Angeles, 1955.
J. Gustafson. Reevaluating Amdahl’s Law. Commun. ACM, 31(5):532–533, 1988. ISSN 0001-0782.
A. Horni, K. Nagel, and K.W Axhausen. Introducing matsim. In The multi-agent transport simulation MATSim, pages 3–7. Ubiquity Press, 2016.
H. Kanezashi and T. Suzumura. Performance optimization for agent-based traffic simulation by dynamic agent assignment. In 2015 Winter Simulation Conference (WSC), pages 757–766. IEEE, 2015.
A. Kesting, M. Treiber, and D. Helbing. General lanechanging model MOBIL for car-following models. J. of Transportation Research Board, 1999(1):86–94, 2007.
K. Nagel and A. Schleicher. Microscopic traffic modeling on parallel high performance computers. Parallel Computing, 20(1):125 – 146, 1994. ISSN 0167-8191.
M. Najdek, H. Xie, and W. Turek. Scaling simulation of continuous urban traffic model for high performance computing system. In International Conference on Computational Science, pages 256–263. Springer, 2021.
E. A O’Cearbhaill and M. O’Mahony. Parallel implementation of a transportation network model. Journal of Parallel and Distributed Computing, 65(1):1–14, 2005.
K. Ramamohanarao, H. Xie, L. Kulik, S. Karunasekera, E. Tanin, R. Zhang, and E.B. Khunayn. SMARTS: Scalable microscopic adaptive road traffic simulator. ACM Trans. on Intelligent Systems and Technology (TIST), 8(2):1–22, 2016.
M. Rickert and K. Nagel. Dynamic traffic assignment on parallel computers in transims. Future Generation Computer Systems, 17(5):637 – 648, 2001. ISSN 0167-739X.
L. Toscano, G. D’Angelo, and M. Marzolla. Parallel discrete event simulation with erlang. In Proceedings of the 1st ACM SIGPLAN workshop on Functional high-performance computing, pages 83–92, 2012.
M. Treiber, A. Hennecke, and D. Helbing. Congested traffic states in empirical observations and microscopic simulations. Physical review E, 62(2):1805, 2000.
W. Turek. Erlang-based desynchronized urban traffic simulation for high-performance computing systems. Future Generation Computer Systems, 79:645–652, 2018.
F. van Wageningen-Kessels, H. Van Lint, K. Vuik, and S. Hoogendoorn. Genealogy of traffic flow models. EURO Journal on Transportation and Logistics, 4 (4):445–473, 2015.
Y. Xu, W. Cai, H. Aydt, M. Lees, and D. Zehe. An asynchronous synchronization strategy for parallel large-scale agent-based traffic simulations. In Proceedings of the 3rd ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, pages 259–269, 2015.
M. Zych, M. Najdek, M. Paciorek, and W. Turek. Distributed architecture for highly scalable urban traffic simulation. In International Conference on Computational Science, pages 517–530. Springer, 2022.
Downloads
Veröffentlicht
Ausgabe
Rubrik
Lizenz
Copyright (c) 2026 Mateusz Najdek, Natalia Brzozowska, Wojciech Turek
Dieses Werk steht unter der Lizenz Creative Commons Namensnennung 4.0 International.
