2019/12/01 by Hossein Rastgoftar, Rastgoftar, Hossein, Ella Atkins +1
Decision Sciences · Engineering · Social Sciences · #FOS: Electrical engineering #Simulation Techniques and Applications #Systems and Control (eess.SY) #Traffic Prediction and Management Techniques #Traffic control and management #Transportation Planning and Optimization #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1912.00565
openalex publication_date 2019/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper offers an integrative data-driven physics-inspired approach to\nmodel and control traffic congestion in a resilient and efficient manner. While\nexisting physics-based approaches commonly assign density and flow traffic\nstates by using the Fundamental Diagram, this paper specifies the flow-density\nrelation using past traffic information recorded in a time sliding window with\na constant horizon length. With this approach, traffic coordination trends can\nbe consistently learned and incorporated into traffic planning. This paper also\nmodels traffic coordination as a probabilistic process and obtains traffic\nfeasibility conditions using linear temporal logic. Model productive control\n(MPC) is applied to control traffic congestion through the boundary of the\ntraffic network. Therefore, the optimal boundary inflow is assigned as the\nsolution of a constrained quadratic programming problem.\n