Abstract
This paper documents the efforts to operationalize the conceptual framework of MIcrosimulation Learning-based Approach to TRansit Assignment (MILATRAS) and its component models of departure time and path choices. It presents a large-scale real-world application, namely the multi-modal transit network of Toronto which is operated by the Toronto Transit Commission (TTC). This large-scale network is represented by over 500 branches with more than 10,000 stops. About 332,000 passenger-agents are modelled to represent the demand for the TTC in the AM peak period. A learning-based departure time and path choice model was adopted using the concept of mental models for the modelling of the transit assignment problem. The choice model parameters were calibrated such that the entropy of the simulated route loads was optimized with reference to the observed route loads, and validated with individual choices. A Parallel Genetic Algorithm engine was used for the parameter calibration process. The modelled route loads, based on the calibrated parameters, greatly approximate the distribution underlying the observed loads. 75% of the exact sequence of transfer point choices were correctly predicted by the off-stop/on-stop choice mechanism. The model predictability of the exact sequence of route transfers was about 60%. In this application, transit passengers were assumed to plan their transit trip based on their experience with the transportation network; with no prior (or perfect) knowledge of service performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Carraresi, P., Malucelli, F., Pallottino, S.: Regional mass transit assignment with resource constraints. Transp. Res. Part B 30, 81–98 (1996)
Florian, M.: Deterministic time table transit assignment. In: Preprints of PTRC Seminar on National Models, Stockholm, Sweden (1998)
Joint Program in Transportation: Transportation tomorrow survey 2001: design and conduct of the survey. Data Management Group, University of Toronto, Joint Program in Transportation (2003)
Ma, T., Abdulhai, B.: Genetic algorithm-based optimization approach and generic tool for calibrating traffic microscopic simulation parameters. J. Transp. Res. Rec. 1800, 6–15 (2002)
Mohamed, M.: Generic parallel genetic algorithm engine for ITS applications. M.A.Sc. Thesis (unpublished), Graduate Department of Civil Engineering, University of Toronto, Toronto (2007)
Nguyen, S., Pallottino, S., Malucelli, F.: A modeling framework for passenger assignment on a transport network with timetables. Transp. Sci. 35(3), 238–249 (2001)
Nielsen, O., Jovicic, G.: A large scale stochastic timetable-based transit assignment model for route and sub-mode choices. In: Proceeding of Seminar F, Transportation Planning Methods, 27th European Transport Forum, Cambridge, UK, vol. 434, pp. 169–184 (1999)
Nuzzolo, A., Russo, F., Crisalli, U.: A doubly dynamic schedule-based assignment model for transit networks. Transp. Sci. 35(3), 268–285 (2001)
Parveen, M., Shalaby, A., Wahba, M.: G-EMME/2: an automatic calibration tool of the EMME/2 transit assignment using genetic algorithms. ASCE J. Transp. Eng. 133(10), 549–555 (2007)
Roorda, M.J., Miller, E.J., Kruchten, N.: Incorporating within-household interactions into a mode choice model using a genetic algorithm for parameter estimation. Transp. Res. Rec. 1985, 171–179 (2006)
Small, A.: The scheduling of consumer activities: work trips. Am. Econ. Rev. 72, 467–479 (1982)
Tong, C.O., Richardson, A.J.: Estimation of time-dependent origin-destination matrices for transit networks. J. Adv. Transp. 18, 145–161 (1984)
TTC Report: Service summary report. Service Planning Department of the Toronto Transit Commission (unpublished) (2001)
Wahba, M.: MILATRS: microsimulation learning-based approach to transit assignment. PhD Thesis, Graduate Department of Civil Engineering, University of Toronto, Canada (2008)
Wahba, M., Shalaby, A.: MILATRAS: a new modelling framework for the transit assignment problem. In: Wilson, N., Nuzzolo, A. (eds.) Schedule-Based Modelling of Transportation Network. Springer, New York (2009a)
Wahba, M., Shalaby, A.: Learning-based departure time and path choice modelling for transit assignment under information provision: a theoretical framework. Presented at the 12th international conference on travel behaviour research, Jaipur, Rajasthan, India, December 13–18, 2009 (2009b)
Wahba, M., Shalaby, A.: On the impacts of where to provide information: modelling passenger’s behaviour using experiential learning. Working paper (2011)
Wang, J., Wahba, M., Miller, E.: A comparison of an agent-based transit assignment procedure (MILATRAS) with traditional approaches. J. Transp. Res. Rec. 2175, 47–56 (2010)
Watkins, C.J.C.H.: Learning from delayed rewards. PhD Thesis, Cambridge University, Cambridge, UK (1989)
Wilson, A.G.: Entropy in Urban and Regional Modelling. Pion, London (1970)
Acknowledgments
This research was supported by the Natural Sciences and Engineering Research Council (NSERC) and the Ontario Graduate Scholarship (OGS) Program.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wahba, M., Shalaby, A. Large-scale application of MILATRAS: case study of the Toronto transit network. Transportation 38, 889–908 (2011). https://doi.org/10.1007/s11116-011-9358-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11116-011-9358-5