Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI
Traffic congestion has become a significant problem that hinders the proper functioning of the transportation system. Traffic congestion forewarning methods can provide traffic management with accurate congestion prediction information, thus taking timely measures to avoid or alleviate traffic congestion. In this paper, we propose a data-plus-model framework-based expressway congestion forewarning method that can be used in the absence of high-quantity and high-quality data. First, we applied historical traffic flow data to determine the approximate extent of the traffic congestion forewarning and fitted a proper traffic fundamental diagram to characterize the traffic flow. Then, the critical congestion forewarning parameters were obtained according to the slope change of the fundamental diagram. Finally, the proposed method was applied to an expressway section in Beijing to forewarn of traffic congestion with multiday historical traffic data. The experimental results show that the proposed method can effectively analyze the trend of traffic flow accurately and quickly give early forewarning of congestion, which is helpful in reducing the occurrence and persistence of congestion.
Traffic congestion occurs when there is a mismatch between the demand for road use and the available capacity. The volume-delay function (VDF) can quantify the relationship between travel time and the volume of traffic on a particular link, and also provide insight into the state of a traffic system, such as whether it is congested or uncongested. In this paper, we present a VDF model that is based on the fundamental diagram and has two main components: (1) an improved VDF with fewer parameters that can handle both congested and uncongested traffic conditions, based on a fundamental diagram, and (2) a model-based VDF practical calibration framework for practical traffic applications that can determine key parameters for a link in a corridor. Our experiments using corridors in Los Angeles and Beijing demonstrate that our proposed analytical methods effectively calculate road impedance under congested conditions. The results indicate that the proposed model is superior to other existing models in terms of the root mean squared error (RMSE) and mean absolute error (MAE). In addition, our calibrated results indicate that the travel time index (TTI) in Los Angeles is 2.12, in Beijing is 1.74. The model proposed in this paper provides a useful calibration tool for enhancing model performance and improving the accuracy of travel time and speed estimates in traffic assignment.
Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow.
This paper presents the Cell Transformer (CeT), which utilizes high-definition (HD) map data to predict future traffic states at signalized intersections, thereby aiding trajectory planning for autonomous vehicles. CeT employs discretized lane segments to emulate the cell transmission model, creating a cell space to forecast vehicle counts across all segments based on historical traffic data. CeT enhances prediction accuracy by distinguishing between different vehicle types by incorporating vehicle-type attributes into vehicle-state representations through multi-head attention. In this framework, cells are modeled as nodes in a directed graph, with dynamic connections representing variations in signal phases, thereby embedding spatial relationships and signal information within dynamic graphs. Temporal embeddings derived from time attributes are integrated with these graphs to generate comprehensive spatial–temporal representations. Utilizing an encoder–decoder architecture, CeT captures dependencies and correlations from past cell states to predict future traffic conditions. Validation using real traffic data from pNEUMA demonstrates that CeT significantly outperforms baseline models in two-phase signalized intersection scenarios, achieving reductions of 11.47% in Mean Absolute Error (MAE), 13.48% in Root Mean Square Error (RMSE), and an increase of 4.36% in Accuracy (ACC). In four-phase signalized intersection scenarios, CeT shows even greater effectiveness, with improvements of 13.36% in MAE, 12.93% in RMSE, and 4.78% in ACC. These results underscore CeT’s superior predictive capabilities and highlight the contributions of its core components.
Volume-delay functions (VDFs) or link performance functions describe the mathematical relationship between traffic volume and the traffic delays experienced by travelers. They are a critical building block of static traffic assignment and related network design problems in strategic planning applications. Various forms of VDFs have been developed for urban highway/arterial links. The selection of the underlying VDF and corresponding parameter calibration can significantly affect the accuracy of traffic assignment. The primary focus of this paper is to systematically review VDF-related research to better connect the practical applications with theoretical fundamentals. Based on the bibliometric analysis, we highlight modeling efforts that tie the traffic flow fundamental diagram (FD) to queueing models and link delay/performance functions under both undersaturated and oversaturated conditions. The second focus is on how temporal factors are considered in characterizing volume-delay relationships, such as within-day peak hours and evolution over many years, and we seek to shed more light on improving modeling consistency across different resolutions. This review paper also examines model calibration efforts using multiple data sources and how VDFs can be systematically enhanced and adapted to model emerging applications and multimodal systems.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
