A Coordinated Ramp Metering Framework Based on Heterogeneous Causal Inference
Coordinated ramp metering (CRM) can improve freeway traffic flow by combining the effects of multiple on-ramps. CRM depends on each on-ramp’s metering effects and the pattern of cooperation. The method’s design is based on the effect of each ramp flow on freeway bottlenecks. In this study, the authors investigated the diverse causal effects of ramp flow on freeway bottlenecks, proposing a CRM method based on the causal effects. Causal inference was performed using loop detector data. The estimated diverse causal effect, which varies across traffic conditions, measures the change of bottleneck occupancy resulting from increases flow in each on-ramp. This information specifies the real time importance of each ramp and can update the weight and metering rate of each ramp controller. Compared with isolated ramp metering, the CRM method reduced travel delay by 26.0% by considering the diverse causal effects of on-ramp flow upstream and downstream of the freeway bottleneck, and reduced travel delay by 5.8%. These results show that heterogeneous causal inference is effective in improving the performance of CRM algorithms.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/10939687
-
Authors:
- Peng, Chang
- Xu, Chengcheng
- Publication Date: 2023-7-1
Language
- English
Media Info
- Media Type: Web
- Pagination: pp 1365-1380
-
Serial:
- Computer-Aided Civil and Infrastructure Engineering
- Volume: 38
- Issue Number: 10
- Publisher: Blackwell Publishing
- ISSN: 1093-9687
- Serial URL: http://onlinelibrary.wiley.com/journal/10.1111/(ISSN)1467-8667
Subject/Index Terms
- TRT Terms: Bottlenecks; Coordination; Freeway operations; On ramps; Ramp metering; Traffic flow
- Subject Areas: Highways; Operations and Traffic Management;
Filing Info
- Accession Number: 01892919
- Record Type: Publication
- Files: TRIS
- Created Date: Sep 12 2023 9:19AM