Departure Time Choice Models in Urban Transportation Systems Based on Mean Field Games

TL;DR

This paper introduces a novel Mean Field Games framework for modeling departure time choices in urban transportation, demonstrating improved efficiency and scalability over existing models through theoretical analysis and real-world case studies.

Contribution

The paper develops a new MFG-based departure time choice model that captures traveler behavior and system dynamics, offering better accuracy and computational efficiency than prior models.

Findings

The model achieves 5.6% lower relative cost compared to existing models.

It converges faster with fewer iterations than traditional methods.

Successfully scales to large real-world cases like Lyon Metropolis.

Abstract

Departure time choice models play a crucial role in determining the traffic load in transportation systems. This paper introduces a new framework to model and analyze the departure time user equilibrium (DTUE) problem based on the so-called Mean Field Games (MFGs) theory. The proposed framework is the combination of two main components including (i) the reaction of travelers to the traffic congestion by choosing their departure times to optimize their travel cost; and (ii) the aggregation of the actions of the travelers, which determines the system level of service. In this paper, we first present a continuous departure time choice model and investigate the equilibria of the system. Specifically, we demonstrate the existence of the equilibrium and characterize the DTUE. Then, a discrete approximation of the system is provided based on deterministic differential game models to numerically obtain the equilibrium of the system. To examine the efficiency of the proposed model, we compare it with the departure time choice models in the literature. We apply our framework to a standard test case and observe that the solutions obtained based on our model are 5.6\% better in terms of relative cost compared to the solutions determined based on models in the literature. Moreover, our proposed model converges with less number of iterations than the reference solution method in the literature. Finally, the model is scaled up to the real test case corresponding to the whole Lyon Metropolis with real demand pattern. The results show that the proposed framework is able to tackle much larger test case than usual to includes multiple preferred travel times and heterogeneous trip lengths more accurately than existing models in the literature.