Real‐Time Distributed Optimization of Traffic Signal Timing

Principal Investigator(s):

Yafeng Yin, Professor of Civil and Environmental Engineering – The University of Michigan
Siqian Shen, Associate Professor of Industrial and Operations Engineering – The University of Michigan
Associate Director – Michigan Institute of Computational Discovery & Engineering (MICDE)
Henry Liu, Director – Center for Connected and Automated Transportation (CCAT)
Director – Mcity
Professor of Civil and Environmental Engineering – The University of Michigan
Research Professor – The University of Michigan Transportation Research Institute

Project Abstract:
Leveraging recent advancements in distributed optimization, and the growing connectivity and computational capability of vehicles and infrastructure, we propose to revolutionize real‐time adaptive signal control via distributed optimization. The proposed research consists of three thrusts. Thrust 1 focuses on advancing distributed optimization and parallel computing techniques for solving network-level signal optimization models with discrete variables, nonconvex/nonlinear objective function and/or constraints. Thrust 2 further distributes the computation task to individual vehicles, by further decomposing distributed intersection‐level subproblems to smaller problems that can be solved at the vehicle level, or treating them as fully independent economic agents that negotiate the right-of‐way through intersections. In Thrust 3, we conduct simulation to validate our results and deploy the system developed in Thrust 1 in the city of Ann Arbor.

Institution(s): University of Michigan Transportation Research Institute
University of Michigan – Ann Arbor

Award Year: 2019

Research Thrust(s): Control & Operations, Enabling Technology, Modeling & Implementation

Project Form(s):
Project Information Form
Final Report