.png){kind=icon}
.png){kind=icon}
Return
Statistical regression-powered optimization methods for path-based congestion pricing at scale
.png){kind=icon}
OA
AI
DOI：10.1016/j.trc.2025.105414.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Highlights • Proposing a statistical regression-powered framework based on machine learning for scalable path congestion pricing optimization. • Develop a sample-generating-based data-synthesis procedure that generates high-fidelity training sets. • Integrate complementary feature-selection techniques to isolate parsimonious yet informative predictor subsets, thereby enhancing model performance • Embed the trained regressor within a surrogate optimization model and iterative algorithm to obtain feasible and efficient solutions to the bilevel optimization problem • Conduct a comprehensive experiment on large-scale transportation networks, demonstrating the proposed framework’s efficiency and computational scalability.
Keywords:
Congestion pricing
Path-based
Traffic assignment
Statistical regression-powered optimization
Machine learning
Bilevel optimization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
T
IF:
0
Papers:
196
Citations:
0
Organization
View more organizations