Data-Driven Variable Speed Limit Design for Highways via Distributionally Robust Optimization

  title={Data-Driven Variable Speed Limit Design for Highways via Distributionally Robust Optimization},
  author={Dan Li and Dariush Fooladivanda and Sonia Mart{\'i}nez},
  journal={2019 18th European Control Conference (ECC)},
This paper introduces an optimization problem and a solution strategy to design variable-speed-limit controls for a highway that is subject to traffic congestion and uncertain vehicle arrivals and departures. By employing a finite data-set of samples of the uncertain variables, we find a data-driven solution that has a guaranteed out-of-sample performance. In principle, such formulation leads to an intractable problem as the distribution of the uncertainty variable is unknown. By adopting a… Expand
Online Optimization and Learning in Uncertain Dynamical Environments with Performance Guarantees
This framework enables us to simultaneously learn the uncertain dynamical environment while making online decisions in a quantifiably robust manner and determines how the proposed solution system achieves a probabilistic regret bound under certain conditions. Expand
Dynamics of Data-driven Ambiguity Sets for Hyperbolic Conservation Laws with Uncertain Inputs
This study investigates the spatio-temporal evolution of data-driven ambiguity sets and their associated guarantees when the random QoIs they describe obey hyperbolic partial-differential equations with random inputs and demonstrates that the ambiguity sets are guaranteed to contain the true (unknown) distributions within a prescribed confidence. Expand
OnlineOptimization andLearning inUncertainDynamical EnvironmentswithPerformanceGuarantees ?
We propose a new framework to solve online optimization and learning problems (P) in unknown and uncertain dynamical environments. This framework enables us to simultaneously learn the uncertainExpand
High-Confidence Data-Driven Ambiguity Sets for Time-Varying Linear Systems
This paper builds Wasserstein ambiguity sets for the unknown probability distribution of dynamic random variables leveraging noisy partial-state observations. The constructed ambiguity sets containExpand
Data-driven Variable Speed Limit Design with Performance Guarantees for Highways
By developing a distributionally robust optimization framework, this paper presents an equivalent and yet tractable reformulation of (P), and proposes an efficient algorithm that provides suboptimal data-driven solutions and guarantees congestion-free conditions with high probability. Expand


Convexity and robustness of dynamic traffic assignment and freeway network control
It is shown, using the Pontryagin maximum principle, that variable speed limits are not needed in order to achieve optimality in the FNC problem, and ramp metering is sufficient, and bounds on perturbation of the controlled system trajectory are proved to be in close agreement with numerical simulation results. Expand
Data-driven distributed optimization using Wasserstein ambiguity sets
  • A. Cherukuri, J. Cortés
  • Computer Science
  • 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • 2017
A data-driven distributionally robust optimization (DRO) problem using Wasserstein ambiguity sets that has the desired performance guarantees is formulated and a distributed algorithm designed as the gradient descent in the convex variable and gradient ascent in the concave variable of this Lagrangian function is designed. Expand
Cooperative Data-Driven Distributionally Robust Optimization
A class of multiagent stochastic optimization problems where the objective is to minimize the expected value of a function which depends on a random variable is studied, to identify a convex–concave augmented Lagrangian, whose saddle points are in correspondence with the optimizers, provided a min–max interchangeability criteria is met. Expand
An exact convex relaxation of the freeway network control problem with controlled merging junctions
This work shows that the control of flows into merging junctions is sufficient to do so if the objective is to minimize the total time spent in traffic, and derives the main result via a characterization of the system dynamics. Expand
Sustainable Model-Predictive Control in Urban Traffic Networks: Efficient Solution Based on General Smoothening Methods
This paper proposes an MPC system for an urban traffic network that applies a gradient-based optimization approach to solve the control optimization problem and introduces efficient smoothening methods for nonsmooth mathematical models of physical systems. Expand
Sufficient optimality conditions for distributed, non-predictive ramp metering in the monotonic cell transmission model
We consider the ramp metering problem for a freeway stretch modeled by the Cell Transmission Model. Assuming perfect model knowledge and perfect traffic demand prediction, the ramp metering problemExpand
On Structural Properties of Feedback Optimal Control of Traffic Flow under the Cell Transmission Model
It is shown that the optimal feedback control can be represented in a closed-form by a piecewise affine function on polyhedra of the network traffic density, and it is demonstrated that, with respect to certain meaningful linear performance indexes, the performance loss due to decentralization is zero. Expand
Online data assimilation in distributionally robust optimization
  • D. Li, S. Martínez
  • Mathematics, Computer Science
  • 2018 IEEE Conference on Decision and Control (CDC)
  • 2018
This paper considers a class of real-time decision making problems to minimize the expected value of a function that depends on a random variable ξ under an unknown distribution P, and proposes a novel Online Data Assimilation Algorithm for this purpose. Expand
Feedback Traffic Control at Highway Work Zones using Variable Speed Limits
A Proportional-Integral feedback regulator is employed for control which is simpler and potentially more robust compared to heuristic or optimal control procedures, and deemed suitable for field implementation. Expand
Stabilizing Traffic with Autonomous Vehicles
This article introduces two conditions which simultaneously stabilize traffic while imposing a safety constraint on the autonomous vehicle and limiting degradation of performance, and formalizes the problem in terms of linear string stability, derive optimality conditions from frequency-domain analysis, and pose the resulting nonlinear optimization problem. Expand