Dynamic Origin-Destination Estimation Framework with Iterative Traffic Signal Tuning for Microscopic Traffic Simulation

To validate traffic signal control algorithm’s performance, a setup of microscopic traffic simulation platform with realistic traffic demand is necessary. Traditionally, a bilevel framework of Origin-Destination (OD) calibration and trip assignment, is setup to estimate OD so that realistic traffic demand can be emulated in simulation platform. However, with this approach, we may mislead the calibration process by introducing insufficient green time allocation, as vehicles are likely to be stopped by red signals and thus vehicle throughput will never reach the real traffic demand. While this happens occasionally in unsaturated traffic condition, it is very prevalent in the saturated condition scenario. This paper introduces a trilevel problem formulation with consideration of traffic signal schedules during the OD estimation process. The first level uses an iterative algorithm (LSQR) to generate OD traffic demand with certain constraints based on real loop count data at junctions. Second level applies the traffic demand into a simulation platform to generate the trips between OD points. Dynamic User Equilibrium (DUE) will be satisfied iteratively so that the trip assignment is reasonable. Finally, the third level applies Iterative Tuning (IT) signal controller to tune signal schedules iteratively, such that sufficient green time can be allocated to allow vehicles drive through intersections. Via OD calibrations in corridor and area networks, we show that the trilevel OD estimation approach can achieve better performance as compared to the bi-level approach.