Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-driven generalized perimeter control: Zürich case study

Alessio Rimoldi, Carlo Cenedese, Alberto Padoan, Florian Dörfler, John Lygeros

Abstract

Urban traffic congestion is a key challenge for the development of modern cities, requiring advanced control techniques to optimize existing infrastructures 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 require 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. 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 and CO2 emissions.

Data-driven generalized perimeter control: Zürich case study

Abstract

Urban traffic congestion is a key challenge for the development of modern cities, requiring advanced control techniques to optimize existing infrastructures 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 require 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. 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 and CO2 emissions.
Paper Structure (30 sections, 1 theorem, 31 equations, 16 figures, 3 tables, 2 algorithms)

This paper contains 30 sections, 1 theorem, 31 equations, 16 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Rule-Based
  4. Dynamic Programming
  5. Distributed and Multi-Agent Methods
  6. Model Predictive Control
  7. Data-enabled Predictive Control
  8. Simulation-based Optimization
  9. Contributions
  10. Notation
  11. Behavioral formulation of urban traffic dynamics
  12. Traffic network, sensing and demand
  13. Intersection Control
  14. Macroscopic fundamental diagram
  15. Behavioral traffic dynamics
  16. ...and 15 more sections

Key Result

Lemma 1

markovsky2022identifiability Consider a system ${\mathcal{B} \in \mathcal{L}^{q}}$ with lag ${\ell\in\mathbb{N}}$ and a trajectory of the system ${w_{\textup{d}} \in \mathcal{B}|_{ [1,T] }}$. Assume ${L > \ell}$. Then $\mathcal{B}|_{ [1,L] } = \operatorname{im} H_L(w_{\textup{d}})$ if and only if where $n$ and $m$ are the order and the number of inputs of the system, respectively.

Figures (16)

  • Figure 1: The city is divided into $p$ regions homogeneous in average traffic density (the hexagons) and the demand $\boldsymbol{d}$ among them. A detail of sensors $\mathbf{s}_j$ (blue diamonds) and traffic lights $\mathbf{l}_j$ (green circles) locations within region $j\in\mathbf{p}$ is shown.
  • Figure 2: Example of a four-legged intersection and compatibility of traffic flows. On the left the structural components of the intersection are highlighted for clarity. On the right the difference between compatible and antagonistic flows can be observed.
  • Figure 3: Example of a duty cycle comprising six phases divided in active and passive. Active phases (slowromancapi@,slowromancapiv@) are grouped in the leftmost column and highlighted in green, while passive phases (slowromancapii@,slowromancapiii@,slowromancapv@,slowromancapvi@) can be found in the two rightmost columns highlighted in red. Active phases have at least one 'g' state in the tuple.
  • Figure 4: Different control input values $\lambda_\ell$ result in different active and passive phase durations, that is $\delta_a$ and $\delta_p$, for a traffic light $\ell\in\mathbf{l}$. The bottom graph shows a possible input trajectory for the $\ell$-th traffic light spanning three duty cycles, the top graph shows proportion of duty cycle time assigned to the active and passive phases as a result of the input.
  • Figure 5: Commutative diagram of the relationships between $\lambda$, $\rho$ and $\phi$. The relationship between $\rho$ and $\phi$ is assumed to be a similar to Figure \ref{['fig:MFD']}.
  • ...and 11 more figures

Theorems & Definitions (1)

  • Lemma 1