Demonstration-Guided Deep Reinforcement Learning for Coordinated Ramp Metering and Perimeter Control in Large Scale Networks

Hu, Zijian; Ma, Wei

doi:10.2139/ssrn.4380256

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mixed road network, combining arterial roads and expressways, offers a more robust and flexible transportation system. Increasingly, such networks are becoming prevalent in urban areas [1]. However, with increasing traffic demand, arterial road networks and expressways in the mixed road network face the congestion risk, bringing economic losses and Submission date: April 25, 2024.…”

Section: Introductionmentioning

confidence: 99%

“…The methods in [26]- [27] focus on modeling and controlling urban intersections and road segments, which, due to computational constraints, are more suitable for localized mixed road networks. Additionally, the coordinated control scheme combining perimeter control within subregions and ramp metering has been proposed in [1] and [28], but the positive role of traffic guidance in solving traffic congestion has not been considered. Compared to conventional arterial networks, the primary distinction of mixed road networks lies in including expressways, which provide alternative travel routes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integrated Control for Mixed CAV and CV Traffic Flow in Expressway Merge Zones Combined with Variable Speed Limit, Ramp Metering, and Lane Changing

Zhang

Ding

et al. 2023

J. Transp. Eng., Part A: Systems

View full text Add to dashboard Cite

Abstract-Facing the congestion challenges of mixed road networks comprising expressways and arterial road networks, traditional control solutions fall short. To effectively alleviate traffic congestion in mixed road networks, it is crucial to clear the interaction between expressways and arterial networks and achieve orderly coordination between them. This study employs the multi-class cell transmission model (CTM) combined with the macroscopic fundamental diagram (MFD) to model the traffic dynamics of expressway systems and arterial subregions, enabling vehicle path tracking across these two systems. Consequently, a comprehensive traffic transmission model suitable for mixed road networks has been integrated. Utilizing the SUMO software, a simulation platform for the mixed road network is established, and the average trip lengths within the model have been calibrated. Based on the proposed traffic model, this study constructs a route guidance model for mixed road networks and develops an integrated model predictive control (MPC) strategy that merges route guidance, perimeter control, and ramp metering to address the challenges of mixed road networks' traffic flow control. A case study of a scenario in which a bidirectional expressway connects two subregions is conducted, and the results validate the effectiveness of the proposed cooperative guidance and control (CGC) method in reducing overall congestion in mixed road networks.

show abstract

Section: Introductionmentioning

confidence: 99%