Optimal information perturbation for traffic congestion mitigation: Gaussian process regression and optimization

Abstract

Information perturbation is an information provision strategy which strategically alters the traffic information sent to drivers, aiming to mitigate network congestion caused by selfish routing decisions. Previous works have integrated information perturbation into coordinated routing mechanisms and theoretically proved that the system performance improvement due to information perturbation is more significant than the corresponding average user optimality loss. However, they do not give direct guidance as to which perturbation level should be implemented to manage the competing effects of system performance improvement and user optimality loss most efficiently. Accordingly, the goal of this work is to uncover the optimal perturbation that should be included in the information sent to vehicles under a coordinated routing scheme under some known network condition. The optimal perturbation problem considers the tradeoff between system performance improvement and user optimality loss due to perturbation, while ensuring that no exorbitant individual user optimality loss occurs. The relationships used in the optimization models are obtained through gaussian process regression, which are trained using the output of computer experiments. We pay special attention to the input features of these models, which impact the system performance and user optimality loss in our model the most—namely the perturbation, demand, and routing competition levels. We model route competition levels through a new parameter called weighted concentration, and present a novel approach for sampling weighted competition values for a single demand level. We present several candidate gaussian process specifications which are used in the optimization, including single and multiple output. Finally, we demonstrate the merit of our methodology through a sensitivity analysis using the Sioux Falls network as a test case. Here, we find that our optimization approach can find robust solutions (in terms of their proximity to local optimums) relatively high rate, with a satisfied solution time.