DYNAMIT 2.0: REAL-TIME MODEL SYSTEM FOR NETWORK MANAGEMENT AND EMERGENCY RESPONSE
DynaMIT is a dynamic traffic assignment (DTA) system for traffic estimation and prediction developed at the MIT Intelligent Transportation Systems Laboratory
DynaMIT 2.0 is a next generation multi-modal traffic state prediction and network control platform, which enhances the original DynaMIT system through the simultaneous/sequential calibration of demand and supply parameters.
The system also includes a strategy optimization module that optimizes network control strategies in real time for congestion mitigation and other objectives.
DynaMIT 2.0 is a multi-modal multi-data source driven, simulation-based short-term traffic prediction system developed by SMART-FM. The system contains a collection of data modules and algorithms that estimate and predict network states in real-time. The main features of DynaMIT 2.0 include: a) the modeling of multiple modes including public transit, mobility-on-demand services such as Uber/Lyft, car and ride sharing, etc.; b) Online calibration of demand and supply parameters using heterogeneous data sources; c) context mining and the scenario analyzer for unstructured data, e.g. traffic incident reports; d) The strategy optimization module for network control strategy optimization. DynaMIT 2.0 performs state estimation and state prediction at each interval of the simulation based on a rolling horizon and is designed to reside within a traffic management system. In the state estimation phase, the current network condition is estimated with real-time traffic information; in the state prediction phase, future short term network conditions are predicted and consistent traffic guidance information and optimal control strategies are determined.
Ben-Akiva, M., H. N. Koutsopoulos, C. Antoniou, and R. Balakrishna, Traffic Simulation with DynaMIT. In Fundamentals of Traffic Simulation (J. Barceló, ed.), Springer, New York, NY, USA, 2010, pp. 363–398.
Gupta S, Seshadri R, Atasoy B, Pereira FC, Wang S, Vu VA, Tan G, Dong W, Lu Y, Antoniou C, Ben-Akiva M. Real time optimization of network control strategies in DynaMIT 2.0. In Transportation Research Board 95th Annual Meeting, 16-5560, 2016.
Lentzakis AF, Seshadri R, Akkinepally A, Vu VA, Ben-Akiva M. Hierarchical density-based clustering methods for tolling zone definition and their impact on distance-based toll optimization. Transportation Research Part C: Emerging Technologies. 2020 Sep 1;118:102685.
Lu L, Xu Y, Antoniou C, Ben-Akiva M. An enhanced SPSA algorithm for the calibration of Dynamic Traffic Assignment models. Transportation Research Part C: Emerging Technologies. 2015 Feb 1;51:149-66.
Lu Y, Seshadri R, Pereira FC, OSullivan A, Antoniou C, Ben-Akiva M. Dynamit2. 0: Architecture design and preliminary results on real-time data fusion for traffic prediction and crisis management. In2015 IEEE 18th International Conference on Intelligent Transportation Systems 2015 Sep 15 (pp. 2250-2255). IEEE.
Pereira, F. C., F. Rodrigues, and M. Ben-Akiva, Text analysis in incident duration prediction. Transportation Research Part C: Emerging Technologies, Vol. 37, 2013, pp. 177–192.
Rodrigues F, Borysov SS, Ribeiro B, Pereira FC. A bayesian additive model for understanding public transport usage in special events. IEEE transactions on pattern analysis and machine intelligence. 2016 Dec 2;39(11):2113-26.