Privacy-Preserving Adaptive Traffic Signal Control in a Connected Vehicle Environment

TL;DR

This paper introduces a privacy-preserving adaptive traffic signal control method using connected vehicle data, employing secure computation and differential privacy to protect individual privacy while maintaining effective traffic management.

Contribution

It proposes a novel privacy-preserving data aggregation mechanism and adaptive control models that balance privacy with traffic efficiency in connected vehicle environments.

Findings

Privacy is preserved with minimal impact on control performance.

Stochastic programming reduces residual queues significantly.

Method guarantees utility and privacy in CV-based traffic control.

Abstract

Although Connected Vehicles (CVs) have demonstrated tremendous potential to enhance traffic operations, they can impose privacy risks on individual travelers, e.g., leaking sensitive information about their frequently visited places, routing behavior, etc. Despite the large body of literature that devises various algorithms to exploit CV information, research on privacy-preserving traffic control is still in its infancy. In this paper, we aim to fill this research gap and propose a privacy-preserving adaptive traffic signal control method using CV data. Specifically, we leverage secure Multi-Party Computation and differential privacy to devise a privacy-preserving CV data aggregation mechanism, which can calculate key traffic quantities without any CVs having to reveal their private data. We further develop a linear optimization model for adaptive signal control based on the traffic variables obtained via the data aggregation mechanism. The proposed linear programming problem is further extended to a stochastic programming problem to explicitly handle the noises added by the differentially private mechanism. Evaluation results show that the linear optimization model preserves privacy with a marginal impact on control performance, and the stochastic programming model can significantly reduce residual queues compared to the linear programming model, with almost no increase in vehicle delay. Overall, our methods demonstrate the feasibility of incorporating privacy-preserving mechanisms in CV-based traffic modeling and control, which guarantees both utility and privacy.