Deep Learning Methods for Adjusting Global MFD Speed Estimations to Local Link Configurations

2024-05-23

arXiv.org

AI Summary

Macroscopic Fundamental Diagram (MFD) models suffer from insufficient link-level speed heterogeneity representation, leading to inadequate accuracy in link-specific speed prediction. Method: This paper proposes a Local Correction Factor (LCF) method that integrates network-wide average speed with topological features to enable precise link-level speed estimation. We innovatively design a spatiotemporal joint modeling framework coupling Graph Attention Networks (GAT) and Gated Recurrent Units (GRU), and introduce a network-partitioning–based LCF generation mechanism to achieve fine-grained correction while preserving the MFD’s high computational efficiency. Contribution/Results: Extensive validation across diverse urban traffic scenarios demonstrates that the proposed approach reduces relative error in path travel time estimation by 76% compared to conventional MFD-only methods. It significantly enhances dynamic link-level representation capability and prediction robustness without compromising scalability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Local Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Large-scale security measurements
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In large-scale traffic optimization, models based on Macroscopic Fundamental Diagram (MFD) are recognized for their efficiency in broad analyses. However, they fail to reflect variations in the individual traffic status of each road link, leading to a gap in detailed traffic optimization and analysis. To address the limitation, this study introduces a Local Correction Factor (LCF) that a function integrates MFD-derived network mean speed with network configurations to accurately estimate the individual speed of the link. We use a novel deep learning framework combining Graph Attention Networks (GATs) with Gated Recurrent Units (GRUs) to capture both spatial configurations and temporal dynamics of the network. Coupled with a strategic network partitioning method, our model enhances the precision of link-level traffic speed estimations while preserving the computational benefits of aggregate models. In the experiment, we evaluate the proposed LCF through various urban traffic scenarios, including different demand levels, origin-destination distributions, and road configurations. The results show the robust adaptability and effectiveness of the proposed model. Furthermore, we validate the practicality of our model by calculating the travel time of each randomly generated path, with the average error relative to MFD-based results being reduced to approximately 76%.

Problem

• Adjusts global MFD speed estimates to local road conditions
• Uses deep learning to correct link-level traffic speed deviations
• Improves travel time accuracy while maintaining computational efficiency

Innovation

• Uses Local Correction Factor (LCF) for speed deviations
• Integrates GATs and GRUs for spatiotemporal analysis
• Reduces travel time error by 84% vs MFD