Abstract
MATSim (Multi-Agent Transport Simulation Toolkit) is an open source large-scale agent-based transportation planning project applied to various areas like road transport, public transport, freight transport, regional evacuation, etc. BEAM (Behavior, Energy, Autonomy, and Mobility) framework extends MATSim to enable powerful and scalable analysis of urban transportation systems. The agents from the BEAM simulation exhibit ‘mode choice’ behavior based on multinomial logit model. In our study, we consider eight mode choices viz. bike, car, walk, ride hail, driving to transit, walking to transit, ride hail to transit, and ride hail pooling. The ‘alternative specific constants’ for each mode choice are critical hyperparameters in a configuration file related to a particular scenario under experimentation. We use the ‘Urbansim-10k’ BEAM scenario (with 10,000 population size) for all our experiments. Since these hyperparameters affect the simulation in complex ways, manual calibration methods are time consuming. We present a parallel Bayesian optimization method with early stopping rule to achieve fast convergence for the given multi-in-multi-out problem to its optimal configurations. Our model is based on an open source HpBandSter package. This approach combines hierarchy of several 1D Kernel Density Estimators (KDE) with a cheap evaluator (Hyperband, a single multidimensional KDE). Our model has also incorporated extrapolation based early stopping rule. With our model, we could achieve a 25% L1 norm for a large-scale BEAM simulation in fully autonomous manner. To the best of our knowledge, our work is the first of its kind applied to large-scale multi-agent transportation simulations. This work can be useful for surrogate modeling of scenarios with very large populations.
K. Chhatre—The work was performed as a Berkeley Lab affiliate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Average One-Way Commuting Time by Metropolitan Areas – census.gov. https://www.census.gov/library/visualizations/interactive/travel-time.html. Accessed 02 May 2022
NCHRP Synthesis 406: Advanced Practices in Travel Forecasting. https://onlinepubs.trb.org/onlinepubs/nchrp/nchrp_syn_406.pdf. Accessed 02 May 2022
Transport Statistics Great Britain 2018 Report. https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/787488/tsgb-2018-report-summaries.pdf. Accessed 02 May 2022
TUMI’s Road Space Requirements Representation. https://www.transformative-mobility.org/assets/publications/Road-Space-Requirements.pdf. Accessed 02 May 2022
TUMI’s Vicious Cycle of Predict and Provide Representation. https://www.transformative-mobility.org/assets/publications/The-Vicious-Cycle-of-Predict-and-Provide.pdf. Accessed 02 May 2022
BEAM Documentation. https://beam.readthedocs.io/. Accessed 02 May 2022
R5: Rapid Realistic Routing on Real-world and Reimagined networks. https://github.com/conveyal/r5. Accessed 02 May 2022
Metropolitan Transportation Commission Website. https://mtc.ca.gov/. Accessed 02 May 2022
Vitalsigns Website. https://www.vitalsigns.mtc.ca.gov/. Accessed 02 May 2022
San Francisco Municipal Transportation Decision Survey 2019. https://www.sfmta.com/sites/default/files/reports-and-documents/2020/01/sfmta_travel_decision_survey_2019.pdf. Accessed 02 May 2022
OpenStreet Platform Website. https://www.openstreetmap.org/. Accessed 02 May 2022
General Transit Feed Specification Platform Website. https://gtfs.org/. Accessed 02 May 2022
Horni, A., et al.: The Multi-Agent Transport Simulation MATSim (2016)
Feygin, S.A., et al.: BISTRO: Berkeley Integrated System for Transportation Optimization. ArXiv abs/1908.03821 (2020): n. pag
Tuma, N.B.: Book Review: Econometric Analysis of Count Data. 3d edition, revised and enlarged. By Rainer Winkelmann. Berlin: Spring-Verlag, 2000. 282 pp. Sociological Methods & Research 31 (2003): 427 - 430
Confidence Z Score. http://www.z-table.com/. Accessed 02 May 2022
Wu, J., Frazier, P.: The Parallel Knowledge Gradient Method for Batch Bayesian Optimization. NIPS (2016)
Ho, Y.-C., Hu, J.: An infinitesimal perturbation analysis algorithm for a multiclass G/G/1 queue. Oper. Res. Lett. 9, 35–44 (1990)
Bergstra, J., et al.: Algorithms for Hyper-Parameter Optimization. NIPS (2011)
Li, L., et al.: Hyperband: a novel bandit-based approach to hyperparameter optimization. J. Mach. Learn. Res. 18, 185:1–185:52(2017)
Jamieson, K.G., Talwalkar, A.S.: Non-stochastic Best Arm Identification and Hyperparameter Optimization. ArXiv abs/1502.07943 (2016): n. pag
Frazier, P.: A Tutorial on Bayesian Optimization. ArXiv abs/1807.02811 (2018): n. pag
Falkner, S., Klein, A., Hutter, F.: BOHB: robust and efficient hyperparameter optimization at scale. ICML (2018)
Forked HpBandSter Project at Commit: 841db4b. https://github.com/kschhatre/HpBandSter/. Accessed 02 May 2022
Pyro Nameserver Project Website. https://pyro4.readthedocs.io/en/stable/nameserver.html. Accessed 02 May 2022
ConfigSpace Project Website. https://automl.github.io/ConfigSpace/master/. Accessed 02 May 2022
Gopal, A.R., et al.: Modeling plug-in electric vehicle charging demand with BEAM, the framework for behavior energy autonomy mobility (2017)
Acknowledgements
The authors would like to thank Artavazd Balaian, Haitam Laarabi, Nikolay Ilin, Jessica Lazarus, Zachary Needell, and Rajnikant Sharma for many insightful conversations and technical support. The research was funded by Berkeley Lab’s fellowship and the German National Scholarship provided by the Hans Hermann Voss Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chhatre, K., Feygin, S., Sheppard, C., Waraich, R. (2023). Parallel Bayesian Optimization of Agent-Based Transportation Simulation. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13810. Springer, Cham. https://doi.org/10.1007/978-3-031-25599-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-25599-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25598-4
Online ISBN: 978-3-031-25599-1
eBook Packages: Computer ScienceComputer Science (R0)