Traffic state prediction plays an important role in intelligent transportation systems, but the complex spatial influence of traffic networks and the non-stationary temporal nature of traffic states ...make it a challenging task. In this study, a new traffic network state prediction model for freeways based on a generative adversarial framework is proposed. The generator based on the long short-term memory networks is adopted to generate future traffic states, and a discriminator with multiple fully connected layers is applied to simultaneously ensure the prediction accuracy. The results of experiments show that the proposed framework can effectively predict future traffic network states and is superior to the baselines.
The identification of important nodes with strong propagation capabilities in road networks is a vital topic in urban planning. Existing methods for evaluating the importance of nodes in traffic ...networks only consider topological information and traffic volumes, the diversity of the traffic characteristics in road networks, such as the number of lanes and average speed of road segments, is ignored, thus limiting their performance. To solve this problem, we propose a graph learning-based framework (MGL2Rank) that integrates the rich characteristics of road networks to rank the importance of nodes. This framework comprises an embedding module containing a sampling algorithm (MGWalk) and an encoder network to learn the latent representations for each road segment. MGWalk utilizes multi-graph fusion to capture the topology of road networks and establish associations between road segments based on their attributes. The obtained node representation is then used to learn the importance ranking of the road segments. Finally, a synthetic dataset is constructed for ranking tasks based on the regional road network of Shenyang City, and the ranking results on this dataset demonstrate the effectiveness of our method. The data and source code for MGL2Rank are available at https://github.com/ZJ726.
A traffic network can be viewed as a geometric graph with the nodes representing traffic infrastructures and the edges standing for the links between these nodes. In order to reduce road congestion ...and enhance traffic efficiency, complex network theory is a widely used research tool. Complex network theory can be used to analyze and evaluate network behaviors for systems with nontrivial structures and dynamical properties. Furthermore, complex network theory can quantitatively capture the structural and dynamical properties of traffic networks. This paper provides a comprehensive review of the complex network-based analysis and dynamics of traffic networks. The measures and properties of complex traffic networks are introduced first. Then the traffic flow characteristics are discussed, and the congestion analysis of complex traffic networks is presented. The robustness of complex traffic networks is also discussed, and the guidance of applying complex network theory in urban transportation is provided. Finally, we highlight a range of challenging open problems that should be addressed in future research and promising research opportunities.
•Measures and properties in complex traffic networks are reviewed.•Traffic flow characteristics and congestion management in complex traffic networks are reviewed.•Robustness in complex traffic networks is discussed.•Future research directions are suggested.
•Reliability of URTNs considering the traffic congestion diffusion is studied.•An improved NLC model under different attack strategies is proposed to simulate cascading failures.•A load ...redistribution method with the impedance function is provided.•Formation time, diffusion speed, and scale of cascading failures are analyzed.
The cascading failures caused by traffic congestion diffusion may deteriorate traffic network reliability. Comprehending urban traffic congestion mechanisms is essential for road network planning and traffic management against cascading failures. To uncover this, the reliability of urban road traffic network (URTN) under cascading failure considering different attack strategies is analyzed. The cascading failure model is established based on the improved nonlinear load-capacity relationship. Five kinds of attack strategies including Strength Attack (SA), Betweenness Centrality Attack (BCA), Eigenvector Centrality Attack (ECA), Closeness Centrality Attack (CCA), and Random Attack (RA) are selected. In particular, the capacity affected by traffic congestion is considered, providing a new perspective for the study of traffic congestion diffusion. A state update equation for networks is proposed to simulate the network congestion diffusion. Finally, a case study is conducted by using the URTN of Shanghai as the background. The results show that the network will experience large-scale congestion when high-importance nodes are attacked. The congestion degree is the highest under CCA strategy, network efficiency is the lowest under ECA strategy, and traffic quality is the poorest under CCA strategy. As the congestion critical failure threshold decreases, the speed and scale of cascading failures caused by traffic congestion diffusion are greater. Maintaining proper traffic management and control capability can largely reduce the cascading effect to a great extent and improve the reliability of the network. The results can provide a research basis for traffic management to improve network reliability.
•Fusion process between signals shows that traffic flow undergoes phase transition.•Traffic network is modelled as an Ising model with traffic flow taking on two states.•Transition from congestion ...becomes more apparent when control undergoes Parrondo switching.
While increasing urban traffic can be an indicator of development, this inevitably results in traffic congestion in urban road networks. Is there a way to manage traffic flow through the control of traffic signals such that the overall network congestion is improved? Traffic light signals can be represented as two states of an Ising model. It is possible for traffic lights to ”communicate” with each other through a fusion process from a remote management control system. This requires collection of information which can be fed to a centralized decision-making control mechanism. We first explore the fusion process between traffic signals and show that it is possible for traffic flow in a city to follow the phase transition as exhibited in the 2D Ising model. The model will be extended to show that a random switching between signalling control mechanisms can result in congested traffic being susceptible to transit out of congestion.
The growing demand for air travel has led to the saturation of air traffic networks. Conventional methods of adding routes to alleviate congestion and reduce delays may not achieve the desired effect ...and even degrade system performance. In this paper, we explore the application of Braess’s Paradox in the reduction of air traffic networks. This counterintuitive phenomenon shows that adding new connections to a network can actually increase the overall network pressure. This study uses Hidden Markov methods and the Viterbi algorithm to match air traffic flow with routes, a machine learning approach and a mathematical method to construct cost functions for flight time and traffic volume, and finally uses genetic algorithm and the A* algorithm to detect Braess’s Paradox edges. We uses ADS-B data from the busy month of July 2019 for a case study of the air traffic network over the UK airspace. The results show that Braess’s Paradox is also applicable to multi-flight level air route networks. Removing such network edges can improve system performance. In one day’s case, the total flight time of the day’s traffic volume decreased from 11509.24 minutes to 10459.97 minutes. This equates to an average savings of 4.99 minutes of flight time per flight, which is significant in controlling delay performance.
Maritime traffic network is essential for navigation efficiency and safety of the maritime transport system. This study proposes a framework for extracting maritime traffic network based on Automatic ...Identification System (AIS) data. The framework consists of maritime traffic pattern recognition, semantic routes extraction, route decomposition, and network generation. Firstly, a data-driven method is introduced to recognize ship behavior patterns and extends the single ship behaviors to regional characteristics to determine the departure-arrival areas. Then, based on the different combination of departure-arrival areas, the ship trajectories are classified to traffic groups. Subsequently, the grid-system is used to rasterize each traffic group, which realizes the fusion of trajectory data and geographic location information. Finally, to obtain the main routes and navigation channels, the extraction method is introduced by establishing the cumulative grid importance function. The main routes, together with the navigation channels, compose the maritime traffic network. The method is applied to AIS data in the Beibu Gulf, and the results show that the traffic network contains 12 stop areas, 4 entry/exit locations, 13 main routes as well as their corresponding navigation channels. It is therefore concluded that the proposed method helps (1) provide a theoretical framework to obtain and analyze the maritime traffic network and (2) enrich navigation channel identification methods for maritime transport management.
•A tangible analytical approach to extract maritime traffic network.•The approach consists of maritime traffic pattern recognition and, maritime network generation.•Machine learning method and grid system method are proposed to group traffic patterns.•The proposed approach is demonstrated using real-world AIS data.•The proposed approach has the potential to support intelligent maritime transport management.
Urban road traffic system is a time-evolving, directed weighted network in which both the topological structure and traffic flow should be considered. In this work, we collect the real-time traffic ...data of Xiaoshan district of Hangzhou city in China, to empirically study the properties of the traffic network. We show that the traffic patterns at different times during a day vary significantly. Specifically, at rush hours, more roads with low average velocity would emerge. Correspondingly, the average weight density at rush hours becomes smaller, while the variance increases, meaning that the traffic becomes more heterogeneous. By introducing a null model in which link weights are randomly shuffled, we find that the connected links are correlated, implying that the congested roads do not emerge at random in the network. Finally, we apply the percolation theory to study the influence of weather on the traffic network. We show that, on a rainy weekday, the traffic is more congested than that on a sunny weekday; while the result is opposite for weekends.
•We construct a time-evolving, directed weighted network based on real traffic data.•The topological structure and the traffic patterns of the network are analyzed.•The percolation theory is applied to study the influence of weather on the network.
•Defining the transition between traffic states as a graph Markov process.•Proposing a graph Markov network (GMN) for spatial–temporal data forecasting.•Graph Markov network can predict traffic ...states and infer missing data simultaneously.
Traffic forecasting is a classical task for traffic management and it plays an important role in intelligent transportation systems. However, since traffic data are mostly collected by traffic sensors or probe vehicles, sensor failures and the lack of probe vehicles will inevitably result in missing values in the collected raw data for some specific links in the traffic network. Although missing values can be imputed, existing data imputation methods normally need long-term historical traffic state data. As for short-term traffic forecasting, especially under edge computing and online prediction scenarios, traffic forecasting models with the capability of handling missing values are needed. In this study, we consider the traffic network as a graph and define the transition between network-wide traffic states at consecutive time steps as a graph Markov process. In this way, missing traffic states can be inferred step by step and the spatial–temporal relationships among the roadway links can be incorporated. Based on the graph Markov process, we propose a new neural network architecture for spatial–temporal data forecasting, i.e. the graph Markov network (GMN). By incorporating the spectral graph convolution operation, we also propose a spectral graph Markov network (SGMN). The proposed models are compared with baseline models and tested on three real-world traffic state datasets with various missing rates. Experimental results show that the proposed GMN and SGMN can achieve superior prediction performance in terms of both accuracy and efficiency. Besides, the proposed models’ parameters, weights, and predicted results are comprehensively analyzed and visualized.