Optimal order-[formula omitted] routing policy for adaptive routing in real road networks

Abstract

In uncertain traffic networks, adaptive routing mechanism is essential in adapting to dynamic traffic changes and making effective routing decisions. Most previous work on adaptive routing commonly ignores the realistic requirement of drivers to select and enter a right lane before intersections, and this would lead to urgent lane changing at intersections that not only violates traffic rules but even causes traffic accidents. This paper redefines the adaptive routing problem in real road networks as an optimal order-k routing policy problem by proposing a novel order-k routing policy. It is a routing mechanism that selects the next k arcs at each decision intersection and the first m arcs are the same with the last m arcs of the k arcs selected at the last decision intersection, which are defined as an m-arc-constrained order-k link. This routing mechanism gives sufficient preparation time for lane changing. We develop a two-phase methodology to handle this problem. To address complex spatio-temporal correlations in real road networks, instead of using the random sampling method, we use a copula-based scenario generation method to generate high-quality scenarios for improving solution performances. A two-stage algorithm integrating the enumeration of m-arc-constrained order-k links and the construction of the optimal routing policy is developed to find the optimal order-k routing policy based on the scenarios generated. Extensive numerical experiments demonstrate the superiority of the optimal order-k routing policy to simultaneously obtain good performances and meet the realistic requirement of drivers’ lane changing.