Dynamic Graph Attention Networks for Travel Time Distribution Prediction in Urban Arterial Roads

TL;DR

This paper introduces FDGNN, a novel dynamic graph neural network framework that models arterial travel time distributions using attentional graph convolution on bidirectional, evolving traffic graphs, improving congestion management and travel time reliability.

Contribution

The paper presents a new FDGNN framework that captures complex spatiotemporal traffic dynamics with dynamic, bidirectional graphs and fusion techniques, advancing travel time prediction methods.

Findings

Accurately models travel time as a normal distribution on arterial roads.

Demonstrates robustness across various traffic conditions and intersection types.

Ensures scalability and real-time applicability using GPU computation.

Abstract

Effective congestion management along signalized corridors is essential for improving productivity and reducing costs, with arterial travel time serving as a key performance metric. Traditional approaches, such as Coordinated Signal Timing and Adaptive Traffic Control Systems, often lack scalability and generalizability across diverse urban layouts. We propose Fusion-based Dynamic Graph Neural Networks (FDGNN), a structured framework for simultaneous modeling of travel time distributions in both directions along arterial corridors. FDGNN utilizes attentional graph convolution on dynamic, bidirectional graphs and integrates fusion techniques to capture evolving spatiotemporal traffic dynamics. The framework is trained on extensive hours of simulation data and utilizes GPU computation to ensure scalability. The results demonstrate that our framework can efficiently and accurately model travel time as a normal distribution on arterial roads leveraging a unique dynamic graph representation of corridor traffic states. This representation integrates sequential traffic signal timing plans, local driving behaviors, temporal turning movement counts, and ingress traffic volumes, even when aggregated over intervals as short as a single cycle length. The results demonstrate resilience to effective traffic variations, including cycle lengths, green time percentages, traffic density, and counterfactual routes. Results further confirm its stability under varying conditions at different intersections. This framework supports dynamic signal timing, enhances congestion management, and improves travel time reliability in real-world applications.