Traffic congestion causes driver frustration and costs billions of dollars annually in lost time and fuel consumption. This paper presents five traffic rerouting strategies designed to be incorporated in a cost-effective and easily deployable vehicular traffic guidance system that reduces travel time. The proposed strategies proactively compute individually tailored rerouting guidance to be pushed to vehicles when signs of congestion are observed on their route. The five proposed strategies are the dynamic shortest path (DSP), the A* shortest path with repulsion (AR*), the random k shortest path (RkSP), the entropy-balanced kSP (EBkSP), and the flow-balanced kSP (FBkSP). Extensive simulation results show that the proposed strategies are capable of reducing the travel time as much as a state-of-the-art dynamic traffic assignment (DTA) algorithm while avoiding the issues that make DTA impractical, such as the lack of scalability and robustness, and high computation time. Furthermore, the variety of proposed strategies allows tuning the system to different levels of tradeoffs between rerouting effectiveness and computational efficiency. In addition, the proposed traffic guidance system can significantly improve the traffic even if many drivers ignore the guidance or if the system adoption rate is relatively low.
16 December 2022 in Data Mining and Knowledge Discovery
Traffic forecasting has attracted widespread attention recently. In reality, traffic data usually contains missing values due to sensor or communication errors. The Spatio-temporal feature in traffic data brings more challenges for processing such missing values, for which the classic techniques (e.g., data imputations) are limited: (1) in temporal axis, the values can be randomly or consecutively missing; (2) in spatial axis, the missing values can happen on one single sensor or on multiple sensors simultaneously. Recent models powered by Graph Neural Networks achieved satisfying performance on traffic forecasting tasks. However, few of them are applicable to such a complex missing-value context. To this end, we propose GCN-M, a Graph Convolutional Network model with the ability to handle the complex missing values in the Spatio-temporal context. Particularly, we jointly model the missing value processing and traffic forecasting tasks, considering both local Spatio-temporal features and global historical patterns in an attention-based memory network. We propose as well a dynamic graph learning module based on the learned local-global features. The experimental results on real-life datasets show the reliability of our proposed method.
Traffic congestion causes driver frustration and costs billions of dollars annually in lost time and fuel consumption. This paper presents three traffic re-routing strategies designed to be incorporated in a cost-effective and easily deployable vehicular traffic guidance system that reduces the effect of traffic congestions. This system collects real-time traffic data from vehicles and road-side sensors and computes proactive, individually-tailored re-routing guidance which is pushed to vehicles when signs of congestion are observed on their route. Extensive simulation results over two urban road networks show that all three strategies, namely multipath load balancing considering future vehicle positions (EBkSP), random multipath load balancing (RkSP), and dynamic shortest path (DSP), significantly decrease the average travel time. EBkSP is the best, with as much as 104% improvement compared to the "no re-routing" baseline. Additionally, it lowers with 34% the re-routing frequency compared to the other strategies. Finally, all strategies offer good improvements even when many drivers ignore the guidance or when the system adoption rate is relatively low.