Data-driven perimeter control: A Zürich case study

Urban traffic congestion is a key challenge for the development of modern cities, requiring advanced control techniques to optimize existing infrastructure usage. Despite the extensive availability of data, modeling such complex systems remains an expensive and time-consuming step when designing model-based control approaches. On the other hand, machine learning approaches may require realistic simulations to bootstrap models, or are unable to deal with the sparse nature of traffic data and enforce hard constraints. We propose a novel formulation of traffic dynamics based on behavioral systems theory and apply data-enabled predictive control to steer traffic dynamics via dynamic traffic light control. We design the control input in the framework of traffic light split control and show that it is able to effectively control general topology intersections. We conjecture an approximately linear relationship between the designed input and the chosen output variable to explain the performance of the method. We find that data-enabled predictive control is able to outperform both linear and non-linear formulations of model-based predictive control and conduct extensive analysis to study the method sensitivity to parameters. A high-fidelity simulation of the city of Zürich, the largest closed-loop microscopic simulation of urban traffic in the literature to the best of our knowledge, is used to validate the performance of the proposed method in terms of total travel time.