Real-time Distributed Optimization of Traffic Signal Timing
dc.contributor.author | Yin, Yafeng | |
dc.contributor.author | Shen, Siqian | |
dc.contributor.author | Feng, Yiheng | |
dc.contributor.author | Fei, Xinyu | |
dc.contributor.author | Yu, Xian | |
dc.contributor.author | Wang, Xingmin | |
dc.contributor.author | Mi, Tian | |
dc.date.accessioned | 2023-02-01T18:17:04Z | |
dc.date.available | 2023-02-01T18:17:04Z | |
dc.date.issued | 2023-02-01 | |
dc.identifier.citation | Suggested APA Format Citation: Yin, Yafeng, Shen, Siqian, Feng, Yiheng, Fei, Xinyu, Yu, Xian, Wang Xingmin, & Mi, Tian, (2021) "Real-time Distributed Optimization of Traffic Signal Timing". CCAT Project No. 13, Center for Connected and Automated Transportation, University of Michigan. | en_US |
dc.identifier.uri | https://hdl.handle.net/2027.42/175728 | en |
dc.description.abstract | Leveraging recent advancements in distributed optimization and reinforcement learning, and the growing connectivity and computational capability of vehicles and infrastructure, we propose to advance real-time adaptive signal control via distributed control and optimization. This report consists of three parts. Part 1 develops distributed algorithms for solving a traffic signal timing optimization problem, which is formulated as a mixed-integer programming model. Specifically, the alternating direction method of multipliers (ADMM) is employed, and a two-stage stochastic cell transmission model (CTM) that considers the uncertainty of traffic demand and vehicle turning ratios is considered. Part 2 proposes a framework that utilizes reinforcement learning to optimize a max pressure controller considering the phase switching loss. The max pressure control is modified by introducing a switching curve, and the proposed control method is proved throughput-optimal in a store-and-forward network. Then the theoretical control policy is extended by using a distributed approximation and position-weighted pressure so that the policy-gradient reinforcement learning algorithms can be utilized to optimize the parameters in the policy network including the switching curve and the weigh curve. Part 3 applies reinforcement learning to traffic signal control in a multi-agent scheme, considering the data availability and implementability. The information extracted from traffic cameras is used to define the state of the agents; the action design is aligned with the NEMA dual-ring convention and bounded by a safety constraint, and the coordination is achieved by a shared reward structure among agents. | en_US |
dc.description.sponsorship | U.S. Department of Transportation Office of the Assistant Secretary for Research and Technology 1200 New Jersey Avenue, SE Washington, DC 20590 (OST-R) | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | CCAT Report No. 13 | en_US |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | traffic signal control | en_US |
dc.subject | distributed optimization | en_US |
dc.subject | maximum pressure control | en_US |
dc.subject | reinforcement learning | en_US |
dc.title | Real-time Distributed Optimization of Traffic Signal Timing | en_US |
dc.type | Technical Report | en_US |
dc.subject.hlbsecondlevel | Civil and Environmental Engineering | |
dc.subject.hlbtoplevel | Engineering | |
dc.contributor.affiliationum | Civil and Environmental Engineering, Department of | en_US |
dc.contributor.affiliationother | Purdue University | en_US |
dc.contributor.affiliationumcampus | Ann Arbor | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/175728/1/Real-time Distributed Optimization of Traffic Signal Timing Final Report.pdf | |
dc.identifier.doi | https://dx.doi.org/10.7302/6942 | |
dc.identifier.orcid | 0000-0001-7010-8664 | en_US |
dc.identifier.orcid | 0000-0003-1059-5303 | en_US |
dc.identifier.orcid | 0000-0003-0435-2786 | en_US |
dc.identifier.orcid | 0000-0002-3780-3216 | en_US |
dc.identifier.orcid | 0000-0003-3117-5463 | en_US |
dc.identifier.orcid | 0000-0002-2854-163X | en_US |
dc.identifier.orcid | 0000-0001-5656-3222 | en_US |
dc.description.filedescription | Description of Real-time Distributed Optimization of Traffic Signal Timing Final Report.pdf : Final Report | |
dc.description.depositor | SELF | en_US |
dc.identifier.name-orcid | Yu, Xian; 0000-0003-1059-5303 | en_US |
dc.identifier.name-orcid | Wang, Xingmin; 0000-0003-0435-2786 | en_US |
dc.identifier.name-orcid | Mi, Tian; 0000-0002-3780-3216 | en_US |
dc.identifier.name-orcid | Yin, Yafeng; 0000-0003-3117-5463 | en_US |
dc.identifier.name-orcid | Shen, Siqian; 0000-0002-2854-163X | en_US |
dc.identifier.name-orcid | Feng, Yiheng; 0000-0001-5656-3222 | en_US |
dc.identifier.name-orcid | Fei, Xinyu; 0000-0001-7010-8664 | en_US |
dc.working.doi | 10.7302/6942 | en_US |
dc.owningcollname | Civil & Environmental Engineering (CEE) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.