Search for: All records

Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. Traditional calibration has been developed based on optimization methods. In this paper, we propose a novel physics-informed, learning-based calibration approach that achieves performances comparable to and even better than those of optimization-based methods. To this end, we combine the classical deep autoencoder, an unsupervised machine learning model consisting of one encoder and one decoder, with traffic flow models. Our approach informs the decoder of the physical traffic flow models and thus induces the encoder to yield reasonable traffic parameters given flow and speed measurements. We also introduce the denoising autoencoder into our method so that it can handle not only with normal data but also corrupted data with missing values. We verified our approach with a case study of Interstate 210 Eastbound in California. It turns out that our approach can achieve comparable performance to the-state-of-the-art calibration methods given normal data and outperform them given corrupted data with missing values. History: This paper has been accepted for the Transportation Science Special Issue on ISTTT25 Conference. Funding: This study was supported by the National Science Foundation [Grant CMMI-1949710] and the C2SMART Research Center, a Tier 1 University Transportation Center. 

The advancements of connected vehicle (CV) technologies promise significant safety, mobility, and environmental benefits for future transportation systems. These benefits will largely rely on the market penetration rate (MPR) of CVs and connected infrastructure. However, higher MPR is not guaranteed to result in greater benefits in a transportation system in some cases even if we do not consider the deployment cost of CVs. Therefore, understanding the optimal CV MPR to achieve the best system benefits is informative and can provide some guidance for transportation agencies to use appropriate incentives or other policies to potentially affect the speed of CV adoption. Instead of using the traditional incremental method, this paper proposed a simulation-based approach combined with Bayesian optimization to determine the optimal CV MPR that achieves the highest performance benefits for a freeway segment. The proposed methodology is tested in the I-210 E (in California, U.S.) simulation freeway segment built and calibrated in Simulation of Urban Mobility software as a case study. The weighted sum of the average total travel time on the mainline and the average queue length of on-ramps is formulated as the objective function to optimize the CV MPR. Different weight combinations are tested as different scenarios. The optimization results of these scenarios show that, when the weight of total travel time is high, the optimal CV MPR tends to be high. On the contrary, when the weight of queue length increases, higher CV MPRs may not guarantee higher benefits for the traffic system. The globally optimal CV MPR can be as low as 3%. The case study also confirms the effectiveness of optimizing the CV MPR based on microsimulation and Bayesian optimization.