Abstract:
CORSIM is a large simulator for vehicular traffic, and is being studied with respect to its ability to successfully model and predict behavior of traffic in a 36 block section of Chicago. Inputs to the simulator include information about street configuration, driver behavior, traffic light riming, turning probabilities at each corner and distributions of traffic ingress into the system.
Data is available concerning the turning proportions in the actual neighborhood, as well as counts as to vehicular input into the system and internal system counts, during a day in May, 2000. Some of the data is accurate (video recordings), but some is quite inaccurate (observer counts of vehicles). Previous utilization of these data was to 'tune' the parameters of CORSIM - in an ad hoc fashion - until CORSIM output was reasonable close to the actual data. This common approach, of simply tuning a complex model to real data, can result in poor parameter choices and will completely ignore the often considerable uncertainty remaining in the parameters.
To overcome these problems, we adopt a Bayesian approach, utilizing both types of data, together with a measurement error model for the inaccurate data, to derive the posterior distribution of turning probabilities and the parameters of the CORSIM input distribution. This posterior distribution can then be used to initialize runs of CORSIM, yielding outputs that reflect that actual uncertainty in the analysis.
Computation must be via Markov Chain Monte Carlo methodology, but this is not feasible because of the expense in running CORSIM. Hence we develop an approximation to CORSIM that can be used directly to carry out the MCMC analysis. The resulting MCMC also has some novel features based on the network structure of the problem.
Keywords:
CORSIM; Microsimulator; Tuning; Networks; MCMC; Fast Model Approximation.
tr133.pdf