Estimating link flow through link speed with sparse flow data sampling

doi:10.1111/mice.13323

Estimating link flow through link speed with sparse flow data sampling

2024-08-28

0

OA

AI

DOI：10.1111/mice.13323

Original

Save

View PDF

Abstract

En 中文

In modern transportation systems, network-wide traffic flow estimation is crucial for informed decision making, strategic infrastructure planning, and effective traffic management. While the limited availability of observed road-segment traffic flow data presents a significant challenge, the emerging collection of Global Navigation Satellite System (GNSS) speed data across the entire network provides an alternative method for estimating the missing traffic flow information. To this end, this paper introduces a novel approach to estimating network-wide road-segment traffic flow. This approach takes advantage of the abundantly available GNSS speed data, coupled with only sparsely observed traffic flow samples. By integrating the principles of dynamic traffic assignment models with sparse recovery techniques, we formulate the problem of traffic flow estimation as a Least Absolute Shrinkage and Selection Operator (LASSO) optimization task. The efficacy and practical applicability of our proposed method are validated through evaluations using both hypothetical and real-world case studies. The experimental findings exhibit a close alignment between the estimated and ground-truth link flows across different time periods. Additionally, the method consistently produces low mean estimation errors for the majority of road segments, underlining the potential for our approach in effectively managing traffic flow estimation for large-scale road networks, particularly in situations characterized by data scarcity.

Keywords:

ORIGIN-DESTINATION MATRICES

DYNAMIC TRAFFIC ASSIGNMENT

NEURAL-NETWORK MODEL

PATH

TRANSPORTATION

CALIBRATION

FORMULATION

SIGNAL

Estimating link flow through link speed with sparse flow data sampling

Abstract

AI Summary

Journal

Organization