Abstract
We propose a dynamic vehicular routing algorithm with traffic prediction for improved routing performance. The primary idea of our algorithm is to use real-time as well as predictive traffic information provided by a central routing controller. In order to evaluate the performance, we develop a microtraffic simulator that provides road networks created from real maps, routing algorithms, and vehicles that travel from origins to destinations depending on traffic conditions. The performance is evaluated by newly defined metric that reveals travel time distributions more accurately than a commonly used metric of mean travel time. Our simulation results show that our dynamic routing algorithm with prediction outperforms both Static and Dynamic without prediction routing algorithms under various traffic conditions and road configurations. We also include traffic scenarios where not all vehicles comply with our dynamic routing with prediction strategy, and the results suggest that more than half the benefit of the new routing algorithm is realized even when only 30% of the vehicles comply.
Highlights
Recent data show that traffic conditions in metropolitan areas continue to worsen with increased wasted hours, extra fuel cost, and travel unreliability, for example, the extra time needed to arrive at destinations [1]
The pseudocode for dynamic routing with prediction is described in Pseudocode 1, where C(t) is the set of all the vehicles arriving at some nodes, X(t) is the state vector representing the current traffic condition, and Xp(i) is a temporary state vector that takes into account the predictive future traffic condition caused by previous rerouted vehicles with I(n), n = 1, . . . , i − 1
We have demonstrated that traffic routing can benefit from using predictive information as it helps reduce travel time and improve road efficiency based on simulation studies
Summary
Recent data show that traffic conditions in metropolitan areas continue to worsen with increased wasted hours, extra fuel cost, and travel unreliability, for example, the extra time needed to arrive at destinations [1]. Intelligent Transportation Systems (ITS) attempt to solve this problem by exploiting the advances in information technology, for example, dynamically controlling traffic lights based on traffic conditions and routing vehicles using current and historical traffic information. The routing system computes the shortest path for a given origin-destination (OD) pair at the request of an individual vehicle and sends the route to each vehicle Such a system may reroute the path as updates of traffic conditions continue to become available [5, 6]. In the Static routing, vehicles follow the routes computed initially without changes, and in Dynamic, vehicles are rerouted periodically like Dynamic with prediction, but only using the current traffic conditions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
