Search

To solve the problems existing in most Chinese historic districts, such as incomplete traffic network planning and unreasonable spatial layout, this paper analyzes the spatial characteristics of motor vehicles in the mixed road section of a historical district and summarizes the application conditions and shortcomings of the model for calculating the Bolankerf lane width and re-calibrates the parameters of the model with the survey data, to determine the formula for calculating the width of motor lanes in different sections of roads. Furthermore, this paper establishes a game model of road space optimization for mixed sections of motor vehicles and non-motor vehicles with the goal of minimizing the generalized travel cost. Finally, by taking the Xiangzimiao historic district as the verification object, this paper draws from the Bolankerf model and the game model to determine the most reasonable road space division plan within blocks.

In this paper, we propose a multi-criteria route recommendation framework that considers real-time spatial–temporal predictions and traffic network information, aiming to optimize a taxi driver’s p...

In the context of Connected and Autonomous Vehicles (CAVs), this paper aims to examine the impacts of CAVs on mixed regular-automated traffic flow with the increase of the market penetration rate, in consideration of on-ramp merging and off-ramp diverging of vehicles. Lane changes are a major part of lateral motions, affecting surrounding vehicles locally and traffic flow collectively. On the basis of reinforcement learning technique, a cooperative lane-changing strategy was first developed to enable farsighted lane-changing behavior by CAVs in favor of traffic efficiency. The 3-lane highway stretch with one on-ramp and one off-ramp was applied in this study. With extensive simulations, the results suggest that the inclusion of CAVs considerably improves traffic flow, mean speed, and traffic capacity. Meanwhile, the existence of on/off-ramps has substantial impacts on the lane-changing processes. This work can shed some light on an aspect of the mixed traffic network dynamics for future mobility.

Previous research studies of traffic networks are mainly based on planar networks and less considered the influence of multilayer networks, which illustrate and represent different appropriate urban traffic modes. Development of rail and road networks is inseparable from the development of a prosperous urban area; thus, research on multilayer networks has scientific potential and fulfils a real need. In this paper, a framework of complex network based integrated multilayer urban growth and optimisation model (CNIMUGOM) is proposed, to analyse the complex relationships between the traffic network structure, the population growth, and the urban land-use. The innovation of this paper is the combination of the traffic complex multilayer networks and the “Four Step Model” (which stands for trip generation, trip distribution, model split, and traffic assignment steps). With the multiobjective, multilayer network coevolution and optimisation model, a more efficient traffic network layout was generated based on different land-use, population density, and travel speed scenarios. Then, this paper has proved that the proposed CNIMUGOM can save the traffic network construction investment, reduce the travel cost, make the urban traffic network more efficient, and decrease the total traffic flow amount. This research has connected the recent complex multilayer network related study and traditional urban economic model based study. The findings of the study afford to improve the current land-use and traffic integrated models and can provide traffic network planning suggestions for urban agglomeration development.

Traffic Assignment Problem (TAP) is a critical issue for transportation and mobility models that deals mainly with the calculus and delivery of best-cost routes for the trips in a traffic network. It is a computationally complex problem focused on finding user equilibrium (UE) and system optimum (SO). The Traffic Weighted Multi-Maps (TWM) technique offers a new perspective for TAP calculus, based on routing decisions using different traffic network views. These TWM are complementary cost maps that combine physical traffic networks, traffic occupation data, and routing policies. This paper shows how evolutionary algorithms can find optimal cost maps that solve TAP from the SO perspective, minimizing total travel time and providing the best-cost routes to vehicles. Several strategies are compared: a baseline algorithm that optimizes the whole network and two algorithms based on extended k-shortest path mappings. Algorithms are analyzed following a simulation-optimization methodology over synthetic and real traffic networks. Obtained results show that TWM algorithms generate solutions close to the static UE traffic assignment methods at a reasonable computational cost. A crucial aspect of TWM is its good performance in terms of optimal routing at the system level, avoiding the need for continuous route calculus based on traffic status data streaming.

Accurate and efficient traffic prediction is the key to the realization of intelligent transportation system (ITS), which helps to alleviate traffic congestion and reduce traffic accidents. Due to the complex dynamic spatial-temporal dependence between traffic networks, traffic prediction is extremely challenging. In previous studies, convolution neural network (CNN) and graph convolution network (GCN) were used to model spatial correlation. However, the non-Euclidean correlation of road network reduces the effect of convolution operator modeling. In addition, only considering the traffic interaction around the concerned points simplifies the influence of traffic network. In order to address the above problems, this article proposes an end-to-end global spatial-temporal graph attention network (GST-GAT), which uses the “global interaction + node query” to model the dynamic spatial-temporal correlation of traffic. In the encoder, the long short-term memory (LSTM) component flexibly transforms the traffic dynamic spatial-temporal graph into feedforward differentiable features. Global traffic interaction is proposed to summarize traffic network context changes and integrate all node features at each moment through a forward calculation. Then, each node computes the influence of traffic global interaction on a single node in parallel, and the spatial-temporal interaction information is adaptive fused by gating fusion mechanism. Finally, the end-to-end network structure is used to train the rich mixed feature coding to generate the traffic prediction status of each node. Experiments on public transportation data sets show that GST-GAT performs better than previous work in terms of accuracy and inference speed.

Efficient and exact algorithms are important for performing fast and accurate traffic network simulations with macroscopic traffic models. In this paper, we extend the semianalytical Lax–Hopf algorithm in order to compute link inflows and outflows with the Lighthill–Whitham–Richards (LWR) model. Our proposed fast Lax–Hopf algorithm has a very low computational complexity. We demonstrate that some of the original algorithm’s operations (associated with the initial conditions) can be discarded, leading to a faster computation of boundary demands/supplies in network simulation problems for general concave fundamental diagrams (FDs). Moreover, the computational cost can be further reduced for triangular FDs and specific space–time discretizations. The resulting formulation has a performance comparable to the link transmission model and because it solves the original LWR model for a wide range of FD shapes, with any initial configuration, it is suitable to solve a broad range of traffic operations problems. As part of the analysis, we compare the performance of the proposed scheme with that of other well-known computational methods.

With the advancement of connected autonomous vehicle (CAV) technology, research on future traffic conditions after the popularization of CAVs needs to be resolved urgently. Bounded rationality of human drivers is essential for simulating traffic flow precisely, but few studies focus on the traffic flow simulation considered bounded rationality in CAV mixed traffic flow. In this study, we introduce random bounded rationality into the hybrid feedback strategy (HFS) under CAV mixed traffic flow to explore the impacts of CAV penetration rate on the trip cost of vehicles. First, we investigated the bounded rationality of drivers, and we found that it follows normal contribution. Then, we proposed HFS considering random bounded rationality and the CAV penetration rate to simulate the traffic condition. The numerical results show that the enhancement of the CAV penetration rate could reduce total trip cost. The research could help us to simulate the CAVs mixed traffic flow more precisely and realistically.

Network macroscopic fundamental diagrams (MFDs) have recently been shown to exist in real-world urban traffic networks. The existence of an MFD facilitates the modeling of urban traffic network dynamics at a regional level, which can be used to identify and refine large-scale network-wide control strategies. To be useful, MFD-based modeling frameworks require an estimate of the functional form of a network’s MFD. Analytical methods have been proposed to estimate a network’s MFD by abstracting the network as a single ring-road or corridor and modeling the flow–density relationship on that simplified element. However, these existing methods cannot account for the impact of turning traffic, as only a single corridor is considered. This paper proposes a method to estimate a network’s MFD when vehicles are allowed to turn into or out of a corridor. A two-ring abstraction is first used to analyze how turning will affect vehicle travel in a more general network, and then the model is further approximated using a single ring-road or corridor. This approximation is useful as it facilitates the application of existing variational theory-based methods (the stochastic method of cuts) to estimate the flow–density relationship on the corridor, while accounting for the stochastic nature of turning. Results of the approximation compared with a more realistic simulation that includes features that cannot be captured using variational theory—such as internal origins and destinations—suggest that this approximation works to estimate a network’s MFD when turning traffic is present.

Increasing number of drivers are switching to electric vehicles (EV) for higher efficiency, lower environmental impact and less maintenance cost. To promote the EV revolution, charging issues of EVs needs to be well addressed. Since the traffic flow of the transportation network and the operating conditions of the power systems are time-varying, it is important to implement real-time charging navigation for EV drivers. In this paper, a novel navigation approach is proposed to search the fast charging station with the lowest overall objective, which consists both of the time consumption and the financial cost. The traffic condition and distribution system loading level are reflected by the time consumption on each road section and locational marginal price (LMP) at each fast charging station, respectively. The LMP can act as a signal to divert the EV load and thus relieve the traffic and power line congestions. The proposed navigation approach is based on the multi-agent system framework utilizing the distributed min/max- consensus and the biased min consensus algorithms. Simulations demonstrate the effectiveness of the proposed navigation approach in different scales of systems.

Queue- and delay-based back-pressure control algorithms are appropriate for homogeneous traffic with strict lane discipline. Every traffic movement does not form a separate queue and vehicular dimensions are highly varied in non-lane-based heterogeneous traffic conditions. In this paper, we propose a novel decentralized, area occupancy-based back-pressure control for a non-lane-based heterogeneous traffic network under V2I communication. The concept of spatial area occupancy and temporal area occupancy combined with back-pressure (SAO-BP and TAO-BP) control are appropriate for heterogeneous traffic in the absence of lane discipline. We conducted an extensive simulation study to illustrate the efficacy of the proposed algorithms using the Vissim-MATLAB simulation environment. Our results suggest that the proposed SAO-BP and TAO-BP control algorithms significantly improve the performance of traffic network compared with vehicle actuated control and aggregated queue-based back-pressure control deployed on the same network.

This paper considers the motion coordination problem of autonomous vehicles in an intersection of a traffic network. The featured challenge is the design of an intersection traffic manager, in the form of a supervisory control algorithm, that regulates the motion of the autonomous vehicles in the intersection. We cast the multivehicle coordination task as an optimization problem, with a one-dimensional search-space. A model- and optimization-based heuristic method is employed to compute the control policy that results in the collision-free motion of the vehicles at the intersection and, at the same time, minimizes their delay. Our approach depends on a computation framework that makes the need for complex analytical derivations obsolete. A complete account of the computational complexity of the algorithm, parameterized by the configuration parameters of the problem, is provided. Extensive numerical simulations validate the applicability and performance of the proposed autonomous intersection traffic manager.

Two bi-level models to reconstruct origin-destination (O-D) demand under congested network are explored in terms of the observed link and route travel times, where one model inputs the known trajectories of observed route travel times and the other model uses both known and unknown trajectories of observed route travel times. The proposed models leverage both the link and route traffic information to determine the network O-D demand that minimizes the distances between the observed and estimated traffic information (O-D, link and route travel times) in the upper-level, and optimize the stochastic user equilibrium (SUE) in the lower-level. Meanwhile, the observed information of travel time can capture the relationships between traffic flow and travel cost/time in congested network. The K-means (hard assignment) and Gaussian mixture model (GMM, soft assignment) clustering methods are presented to identify the trajectories of observed route travel times. An iterative solution algorithm is proposed to solve the built O-D reconstruction models, where the method of gradient descent, the method of successive average and Expectation-Maximization (EM) algorithm are used to solve the upper-level model, lower level model, and GMM, respectively. Results from numerical experiments demonstrate the superiority of the travel time based model over the traditional flow based method in congested traffic network, and also suggest that using both the route and link information outperforms only using link information in the reconstruction of O-D demand.

There are considered changes of automotive transports’ emission volumes factors on different territorial level. The emissions’ dynamic in Central Federal district and in Moscow was shown. At the local level the determining factor in vehicle pollutions’ is changing in building density and transport and planning structure. Pollution reduction in Moscow has a center-peripheral gradient and occurs in areas where the road network transformation is combined with the development of the public transport system.

Based on relevant complex network theory, this paper analyzes the characterization parameters of traffic network complexity, such as the causes of traffic congestion and evacuation models. From the perspective of the traffic capacity of traffic network nodes, combined with the transit time of each road, model is proposed for selecting the weights of congestion evacuation nodes. According to the evacuation target, combined with characteristic parameters, such as node degree, node strength, clustering coefficient and closeness, the grey system evaluation method and the analytic hierarchy process (AHP)are combined. Based on the grey relational analysis model, a model is established for determining the priority connectivity evaluation value of each node. The complex characteristics of the actual traffic network in the Chaoyang District of Changchun City are analyzed, then the selection weights of each node of the traffic network are obtained. Having defined the distance between complex network nodes, a congestion evacuation path selection model is proposed, and an evacuation path scheme is given for specified start and end points. Published version

Booming electric vehicles (EVs) lead to degraded quality-of-service (QoS) of urban public charging network (UPCN) consisting of public charging stations (PCSs) and traffic network, such as prolonged waiting time at popular PCSs. UPCN QoS analysis creates broad prospects in QoS optimization by providing reliable tools to improve UPCN performance. Conventional methods focusing on the impact of network topology on QoS underestimates effects of network capacity and its distribution among PCSs. In this paper, we proposed a heterogeneous UPCN model with limited PCS service capacity, and constructed a QoS analysis method according to PCS and EV characteristics from classic method for traffic assignment model, in which we analyzed waiting time at PCSs by queueing theory and calculated feasible routes for EVs recharging half-way by screening from deep-first-search results. Finally, we demonstrated an application of the proposed model and method in QoS optimization. We carried out experiments on popular Sioux Falls network with randomly-added PCSs. Results indicate that proportion of traditionally neglected waiting time at PCSs may reach 22% in EVs' total travel time if fast charging piles serve 2 vehicles/h, and the gap between our method and conventional method in average waiting time and spatial throughput distribution is growing as EV amount increases. These results support our method's advantages in simulating EVs' charging choice trade-off between farther routes and popular PCSs as well as higher performance in UPCN QoS optimization.

Modeling congestion effects arising from multiple travel modes, shared mobility modes in particular, is non-trivial because of the complex interactions among diverse agents and distinct traffic flow compositions. This research aims to provide a theoretical framework of generic traffic network equilibria to unify these services and hopefully become a step stone to modeling shared mobility services in congested road network. In the proposed framework, we mainly focus on three modes: driving solo, ridesharing, and e-hailing service. The four types of traffic flows are: personal vehicle drivers, e-hailing drivers, ridesharing riders, and e-hailing passengers. The first two flows contribute to traffic congestion while the latter two do not. To capture their interactions, a super extended network is created with four copied networks each of whom represents one type of traffic flow. The equilibrium of new mobility systems can then be reformulated as a quasi-variational inequality and solution existence is discussed. The numerical results are tested in both Braess network and Sioux Falls network to illustrate the impact of different parameters on equilibrium outcomes, including modal cost, system travel time and deadhead miles. The results of this model will help assist transportation planners in making policy and regulation decisions regarding shared mobility services.

Previous urban traffic network-based studies have been based mostly on single-layer networks. Based on their shortcomings, starting from the perspective of a multilayer urban traffic network, this paper takes the different anticongestion abilities and network characteristics of various network structures under the condition of traffic congestion as the research object. Then, a comparative experiment is performed via simulation, and the optimal multilayer urban traffic network topology is obtained under different conditions. It is found that these scale-free related multilayer networks have relatively strong ability to support more traffic flows and have higher anticongestion abilities, regardless of whether it is a lower-layer or upper-layer network. The research results are helpful to deepen our understanding of the characteristics of traffic network structures, help scholars further cognize the structural properties of multilayer urban traffic networks, practically help urban traffic network planners to further optimize the urban traffic network, and broaden the study of multilayer traffic networks.

This study aims to demonstrate a new approach for estimating fuel consumption from vehicles circulating on urban roads with different levels of congestion. A microscopic dynamic traffic model (AIMSUN) was coupled with an instantaneous emissions model (CRUISE) and their output was used to refine the average speed model (COPERT) functions. The integrated methodology was applied in an urban corridor in Turin using two validated vehicle models of Euro 5 passenger cars. Three traffic conditions were examined, corresponding to free-flow, normal and congested traffic. New average speed – fuel consumption functions were developed for free and congested traffic, which successfully estimated the differences in fuel consumption when moving from normal to other conditions. The results showed that under congested conditions the fuel consumption can increase by more than 18% in some cases, indicating the significance of incorporating similar congestion algorithms in macro emission models. Moreover, if a more comprehensive method does not exist, the standard COPERT functions could be used to estimate fuel consumption under congested traffic conditions.

The ever increasing demand for air travel is likely to induce air traffic congestion which will elicit great economic losses. In the presence of limited airspace capacity as well as the saturated airway network, it is no longer practicable to mitigate air traffic congestion by adding new airways/links. In this paper, we provide a “counter-intuitive” perspective towards air traffic congestion mitigation by removing airways/links from a given airway network. We draw inspiration from Braess’s Paradox which suggests that adding extra links to a congested traffic network could make the traffic more congested. The paper explores whether Braess’s Paradox occurs in airway networks, or more specifically, whether it is possible to better distribute the flow in an airway network by merely removing some of its airways/links. In this paper, We develop a method for Braess’s Paradox detection in any given airway network. To validate the efficacy of the method, a case study is conducted for the South-East Asia airspace covering Singapore airway network, by using 6 months of ADS-B data. The results show that Braess’s Paradox does occur in airway networks and the proposed method can successfully identify the airway network links that may cause it. The results also demonstrate that, upon removing such links, the total travel time for a given day traffic at a given flight level, was reduced from 8661.15 min to 8328.64 min, a reduction of 332.5 min. This amounts to a saving of 3.8% in travel time. Civil Aviation Authority of Singapore (CAAS) Accepted version The authors thank the anonymous reviewers for their insightful comments and suggestions which contribute a great deal to the quality enhancement of our work. This research is partially supported by SUG Research Grant M4082126.050 by School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore and NTU-CAAS Research Grant M4062429.052 by Air Traffic Management Research Institute, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore.

In this paper, a new mixed steepest descent algorithm which has short computation time and stable solution is provided. Comparisons and case studies based on different traffic network and distance are made with other intelligent and exact algorithms. The large-scale experiment shows that the possibility of securing the optimal solution is greater than 99.5% and the average computation time is lower than 0.06 s when the node scales are less than 50. The proposed algorithm can not only be applied in emergency logistics problems but is also useful for solving other real-world problems.

Complex network theory is a multidisciplinary research direction of complexity science which has experienced a rapid surge of interest over the last two decades. Its applications in land-based urban traffic network studies have been fruitful, but have suffered from the lack of a systematic cognitive and integration framework. This paper reviews complex network theory related knowledge and discusses its applications in urban traffic network studies in several directions. This includes network representation methods, topological and geographical related studies, network communities mining, network robustness and vulnerability, big-data-based research, network optimization, co-evolution research and multilayer network theory related studies. Finally, new research directions are pointed out. With these efforts, this physics-based concept will be more easily and widely accepted by urban traffic network planners, designers, and other related scholars.

Reasonable traffic network model and flexible traffic control strategy play important roles in improving the urban traffic control efficiency. Introducing granular computing theory into traffic network modeling and traffic control is a useful attempt, since granular computing is closer to the human thinking in solving problems. In this paper, the traffic elements are depicted using S-rough set to achieve the granulation partition of traffic network. Four layers are partitioned in the proposed hierarchical multigranularity traffic network model, such as vehicle layer, platoon layer, segment and intersection layer, and subregion layer. Each traffic granule is represented in rough representation form, and the dynamic characteristics are described using the elementary transfer operations based on S-rough set theory. As an application on the proposed traffic network model, an extended max-pressure traffic control strategy is applied on the platoon and segment and intersection layer. Simulation results illustrate that the proposed traffic network model and traffic control strategy achieve better performance.

This paper proposes a novel model-free adaptive control (MFAC) strategy for urban road traffic network via perimeter control based on dynamic linearization technique and predictive control. The accurate traffic flow model of the urban road network is replaced by equivalent data model. Based on the idea of predictive control, the current control action is obtained by solving online, at each sampling coordinate, a finite horizon closed-loop optimal control problem. The robustness of the MFAC strategy to time-varying desired vehicle accumulation, random traffic demand and macroscopic fundamental diagram (MFD) model uncertainty is verified through simulation results.

Traffic speed prediction, as one of the most important topics in Intelligent Transport Systems (ITS), has been investigated thoroughly in the literature. Nonetheless, traditional methods show their limitation in coping with complexity and high nonlinearity of traffic data as well as learning spatial-temporal dependencies. Particularly, they often neglect the dynamics happening to traffic network. Attention-based models witnessed extensive developments in recent years and have shown its efficacy in a host of fields, which inspires us to leverage graph-attention-based method to handling traffic network speed prediction. In this paper, we propose a novel deep learning framework, Spatial-Temporal Graph Attention Networks (ST-GAT). A graph attention mechanism is adopted to extract the spatial dependencies among road segments. Additionally, we introduce a LSTM network to extract temporal domain features. Compared with previous related research, the proposed approach is able to capture dynamic spatial dependencies of traffic networks. A series of comprehensive case studies on a real-world dataset demonstrate that ST-GAT supersedes existing state-of-the-art results of traffic speed prediction. Furthermore, outstanding robustness against noise and on reduced graphs of the proposed model has been demonstrated through the tests.

Real-time traffic network management systems are envisioned to provide network operators with decision support capabilities to alleviate recurrent and non-recurrent congestion. These capabilities involve predicting the network congestion dynamics and facilitating the development of proactive traffic management schemes that integrate traffic control and demand management strategies. However, traffic networks are subject to numerous sources of stochasticity that make it difficult to accurately predict their operational conditions and generate effective traffic management schemes to cope with these conditions. This paper presents a decision support system for proactive-robust traffic network management, which accounts for uncertainty in the network operational conditions. The objective is to develop robust traffic management schemes such that the network overall performance remains close to optimality under all possible future operational conditions. The modeling framework of the system is presented, which adopts a rolling horizon framework that integrates a meta-heuristic search algorithm and a dynamic traffic assignment simulation-based methodology. The system performance is examined through application to the traffic network of the US-75 corridor in Dallas, TX, USA.

The automobile has become an essential element in the daily life of people. In the urban traffic network, an intersection is the ``bottleneck point'' of road network capacity. Most cities in Latin America have a traditional single control system or none. In this context, adequate programming of the traffic light cycles helps to reduce vehicles' waiting time and improve traffic flow. In this paper, we compare five metaheuristics to minimize vehicles' waiting time and maximize the velocity of vehicles in two real scenarios of Argentina and Uruguay. Analysis of experimental results shows that the proposed model optimizes the vehicular flow in a multiple-junction urban traffic network with different topologies and traffic flow.

This research addresses the phenomenon of varying bicycle friendliness in urban areas and considers which elements are necessary to design a city in a bike-friendly manner. It aims to provide a deeper understanding of the term bikeability, in relation to the established term walkability, and methods to create models that measure the degree of bikeability in urban areas. We explain different established models and compare their computational bases. The focus of this paper is to define a computational methodology built within a Geographic Information System (GIS) and a subsequent evaluation based on an investigation area in Munich, Germany. We introduce a bikeability index for specific investigation areas and geovisualize four selected factors of this index. The resulting map views show the road segments of the traffic network where the conditions for biking are adequate, but also those segments which need to be improved.

Traffic congestion is becoming a critical problem in urban traffic planning. Intelligent transportation systems can help expand the capacity of urban roads to alleviate traffic congestion. As a key concept in intelligent transportation systems, urban traffic networks, especially dynamic traffic networks, can serve as potential solutions for traffic congestion, based on the complex network theory. In this paper, we build a traffic flow network model to investigate traffic congestion problems through taxi GPS trajectories. Moreover, to verify the effectiveness of the traffic flow network, an actual case of identifying the congestion areas is considered. The results indicate that the traffic flow network is reliable. Finally, several key problems related to traffic flow networks are discussed. The proposed traffic flow network can provide a methodological reference for traffic planning, especially to solve traffic congestion problems.

Accurate traffic prediction is indispensable to realize an intelligent transportation system in a smart city. However, the traffic network has a complex spatial structure, and short-term / long-term time dependence. Besides, the traffic network is faced with the various external factors, including the instability of hardware equipment in data collection and network time delay in the process of data transmission. And most of the existing methods predict the traffic flow under the traffic data is complete, which lose the tolerance in the case of abnormal data. In this paper, to improve the robustness of the traffic flow prediction model, we propose a multi-task graph convolution network (MTGCN) structure, which combines multi-task learning (MTL) with graph convolution network (GCN). Firstly, the GCN method is used to obtain the spatiotemporal correlation of traffic network. Secondly, we use a model that is able to do MTL via multiple outputs, each corresponding to the same traffic network at different adjacent time durations. Experiments on real traffic flow data sets demonstrate the effectiveness and robustness of the proposed method in the presence of abnormal patterns such as Gaussian noise and random missing.

In this paper, a planning method of transportation-power coupled system based on road expansion model is proposed. First of all, based on the Wardrop equilibrium state, the traffic flow is distributed, to build the road expansion model and complete the traffic network modeling. It is assumed that the road charging demand is directly proportional to the road traffic flow, and the charging facilities will cause a certain degree of congestion on the road. This mutual influence relationship to establish a coupling system of transportation network and power network is used for the planning. In the planning method, the decision variables include the location of charging facilities, the setting of energy storage systems and the road expansion scheme. The planning goal is to minimize the investment cost and operation cost. The CPLEX solver is used to solve the mixed integer nonlinear programming problem. Finally, the simulation analysis is carried out to verify the validity and feasibility of the planning method, which can comprehensively consider the road expansion cost and travel time cost, taking a coupled system of 5-node traffic system and IEEE14 node distribution network as example.

Advancement in the novel technology of connected vehicles has presented opportunities and challenges for smart urban transport and land use. To improve the capacity of urban transport and optimize land-use planning, a novel real-time regional route planning model based on vehicle to X communication (V2X) is presented in this paper. First, considering the traffic signal timing and phase information collected by V2X, road section resistance values are calculated dynamically based on real-time vehicular driving data. Second, according to the topology structure of the current regional road network, all predicted routes are listed based on the Dijkstra algorithm. Third, the predicted travel time of each alternative route is calculated, while the predicted route with the least travel time is selected as the optimal route. Finally, we design the test scenario with different traffic saturation levels and collect 150 sets of data to analyze the feasibility of the proposed method. The numerical results have shown that the average travel times calculated by the proposed optimal route are 8.97 seconds, 12.54 seconds, and 21.85 seconds, which are much shorter than the results of traditional navigation routes. This proposed model can be further applied to the whole urban traffic network and contribute to a greater transport and land-use efficiency in the future.

This paper presents a novel method for predicting the traffic speed of the links on large-scale traffic networks. We first analyze how traffic flows in and out of every link through the lowest cost reachable paths. We aggregate the traffic flow conditions of the links on every hop of the inbound and outbound reachable paths to represent the traffic flow dynamics. We compute a new measure called traffic flow centrality (i.e., the Z value) for every link to capture the inherently complex mechanism of the traffic links influencing each other in terms of traffic speed. We combine the features regarding the traffic flow centrality with the external conditions around the links, such as climate and time of day information. We model how these features change over time with recurrent neural networks and infer traffic speed at the subsequent time windows. Our feature representation of the traffic flow for every link remains invariant even when the traffic network changes. Furthermore, we can handle traffic networks with thousands of links. The experiments with the traffic networks in the Seoul metropolitan area in South Korea reveal that our unique ways of embedding the comprehensive spatio-temporal features of links outperform existing solutions.

Traffic flow prediction is an important foundation for intelligent transportation systems. The traffic data are generated from a traffic network and evolved dynamically. So spatio-temporal relation exploration plays a support role on traffic data analysis. Most researches focus on spatio-temporal information fusion through a convolution operation. To the best of our knowledge, this is the first work to suggest that it is necessary to distinguish the two aspects of spatial correlations and propose the two types of spatial graphs, named as geographic graph and semantic graph. Then two novel stereo convolutions with irregular acceptive fields are proposed. The geographic-semantic-temporal contexts are dynamically jointly captured through performing the proposed convolutions on graph sequences. We propose a geographic-semantic-temporal graph convolutional network (GST-GCN) model that combines our graph convolutions and GRU units hierarchically in a unified end-to-end network. The experiment results on the Caltrans Performance Measurement System (PeMS) dataset show that our proposed model significantly outperforms other popular spatio-temporal deep learning models and suggest the effectiveness to explore geographic-semantic-temporal dependencies on deep learning models for traffic flow prediction.

The article describes sustainable transport principles and guides that can lead cities towards a more efficient transportation network. The authors also show good practice used in different urban areas, such as London and Copenhagen. Furthermore, Vilnius was analyzed for its sustainable transport rules and mobility. The authors took into consideration components such as public transport indicators, car use and the number of trips made by bicycle and by pedestrians. Additionally, solutions such as shared space, developing cycle routes and public transportation networks, dividing different transport modes, reducing distance and the need to travel, policy shifts and technological innovation are proposed. Moreover, already taken actions are also verified. The article, additionally, shows guidance for Vilnius, so it could be possible to develop a sustainable traffic network in the city. All analyses and guidance were based on using geographic information system (GIS) tools which allowed the authors to obtain the most reliable results. The artefacts are presented by means of a combination of graph theory algorithms in order to obtain sustainable transport using the example of a part of Vilnius City.

Coordinated evolution is a process with complexity, temporality, spatiality, and continuity. The existed methods cannot relevantly satisfy and measure the degree of coordinated evolution in real conditions. Aiming at solving the coordinated evolution problems for the urban traffic network, the information complexity must be evaluated, this paper uses the multi-dimensional connection number for compressing the factors of traffic network. Firstly, the basic characteristics of traffic network are analysed on the definition of traffic information complexity. The traffic network measurement model is established based on the information entropy, and the coordinated evolution rocess of the multi-layer urban traffic network is analysed for defining the ordered parameters of the traffic network. Then the coordinated measurement model for the multi-layer traffic network is constructed by the ordered parameters. In addition, we set up a coordinated evolution model according to the proposed estimation criteria of the ordered parameters and the theory of the multi-dimensional connection numbers. The case analysis shows that the order degree of Hangzhou traffic network is 0.7929, which approaches to 1 as while the comprehensive coordinated index of Hangzhou multi-layer traffic network is 0.3323, which clearly and intuitively gives a measurement value for the multi-layer urban traffic network. The result is also effectively verified the validity of the proposed models.

In recent years, different techniques to address the problem of observability in traffic networks have been proposed in multiple research projects, being the technique based on the installation of automatic vehicle identification sensors (AVI), one of the most successful in terms of theoretical results, but complex in terms of its practical application to real studies. Indeed, a very limited number of studies consider the possibility of installing a series of non-definitive plate scanning sensors in the elements of a network, which allow technicians to obtain a better conclusions when they deal with traffic network analysis such as urbans mobility plans that involve the estimation of traffic flows for different scenarios. With these antecedents, the contributions of this paper are (1) an architecture to deploy low-cost sensors network able to be temporarily installed on the city streets as an alternative of rubber hoses commonly used in the elaboration of urban mobility plans, (2) a design of the low-cost, low energy sensor itself, and (3) a sensor location model able to establish the best set of links of a network given both the study objectives and of the sensor needs of installation. A case of study with the installation of as set of proposed devices is presented, to demonstrate its viability.

In this article, a method of traffic state prediction at intersection based video data is proposed. The method inherits the basic assumption of modified cell transmission model (MCTM) and depends on back propagation neural network (BPNN). The training set of the neural network consists of traffic data from the video. In order to verify the good generalization of the prediction method, novel data is used as the verification set. The experimental results exhibit that the model has virtuous generalization. Especially, the model is suitable for short-term traffic prediction at intersections. The prediction results of the method serve to construct the traffic state prediction model (TSPM) of the urban traffic network. Moreover, making route arrangement and traffic guidance strategy also require them.

Traffic flow estimates play a key role in traffic network management and planning of transportation networks. Commonly it is the average daily traffic (ADT) flow for different road segments that constitute the data. This paper shows how an advanced and detailed analysis based on hourly flow measurements over the day can contribute to a deeper understanding of how hourly flows together reflect the vehicles’ routes. The proposed method identifies the shortest travel time paths between all possible origins and destinations in a transportation network, and thereafter it identifies the most significant routes in the network by performing statistical tests. For this purpose, the paper presents a mathematical model, a vehicle simulator based on this model, and a statistical framework that is able to find the most probable underlying routes. The paper contains a real test scenario based on 24-hour traffic flows (hour by hour) to demonstrate the applicability of the method.

In order to control and reduce the congestion in motorway traffic networks, it is required to measure important traffic variables, e.g. densities, that can be observed by sensors. However, to reduce the operational costs, one should look for the most efficient methods to place the minimum number of sensors in a given network. In this paper, we discuss the structural observability of a traffic system, namely, the density dynamics defined on a motorway ring road. For this purpose, LWR theory in a spatial discretization form is employed, and the nonlinear dynamics of the traffic density associated with different cells of the network have been derived. Then, by considering a linearization of the ordinary differential equations (ODEs), we derive the minimum number of sensors that are needed to render the network weakly or strongly structurally observable. In this framework, the parameters of the system can have any nonzero value, and the exact value of nonzero elements (weights) is not of interest. In this work, we also discuss optimal locations in the traffic network to place the minimum set of sensors.

This paper studies travelers&rsquo, context-dependent route choice behavior in a risky trafficnetwork from a long-term perspective, focusing on the effect of travelers&rsquo, salience characteristics. In particular, a flow-dependent salience theory is proposed for this analysis, where the flow denotes the traffic flow on the risky route. In the proposed model, travelers&rsquo, attention is drawn to the salient travel utility, and the objective probabilities of the state of the world are replaced by the decision weights distorted in favor of this salient travel utility. A long-run user equilibrium will be achieved when no traveler can improve his or her salient travel utility by unilaterally changing routes, termed salient user equilibrium, which extends the scope of the Wardropian user equilibrium. Furthermore, we prove the existence and uniqueness of this salient user equilibrium. Finally, numerical studies demonstrate our theoretical findings. The equilibrium results show non-intuitive insights into travelers&rsquo, route choice behavior. (1) Travelers can be risk-seeking (the travel utility of a risky route is small with a relatively high probability), risk-neutral (in special situations), or risk-averse (the travel utility of a risky route is large with a relatively high probability), which depends on the salient state. (2) The extent of travelers&rsquo, risk-seeking or risk-averse behavior depends on their extent of salience bias, while the risk-neutral behavior is irrelative to this salience bias.

Traffic signal control is an important part of the urban traffic control system, and it is a challenging problem to provide effective traffic signal control for a large complex traffic network. In order to improve the traffic efficiency of road network intersections and reduce the congestion of road networks, we optimize the traffic signals at intersections based on the Stochastic Link Flow Model (SLFM). In this paper, the Stochastic Link Flow Model is briefly introduced and the green splits of traffic signal are used as the optimization variables to optimize the traffic flow density, which is described as a stochastic switching of four different link state modes within the traffic network. Lastly, we verified the results with Matlab simulations and confirmed the efficiency of our optimization results.

In recent years, local governments have paid more and more attention to the construction of urban rail transit represented by subways. The subway can greatly improve the ground traffic congestion in the city and the urban traffic environment, making people's travel more convenient. The analysis and accurate prediction of subway passenger flow has always been one of the key tasks of urban rail transit management departments. Especially in the context of the rapid growth of rail transit capacity and the changing needs of passengers, the need for passenger flow analysis is even more significant. This article completes the analysis of Shenzhen's subway passenger flow through big data analysis. It is of great significance to solve urban congestion, optimize the traffic network, and protect public transportation.

The accurate forecasting of urban taxi demands, which is a hot topic in intelligent transportation research, is challenging due to the complicated spatial-temporal dependencies, the dynamic nature, and the uncertainty of traffic. To make full use of the global and local correlations between traffic flows on road sections, this paper presents a deep learning model based on a graph convolutional network, long short-term memory (LSTM), and multitask learning. First, an undirected graph model was formed by considering the spatial pattern distribution of taxi trips on road networks. Then, LSTMs were used to extract the temporal features of traffic flows. Finally, the model was trained using a multitask learning strategy to improve the model&rsquo, s generalizability. In the experiments, the efficiency and accuracy were verified with real-world taxi trajectory data. The experimental results showed that the model could effectively forecast the short-term taxi demands on the traffic network level and outperform state-of-the-art traffic prediction methods.

Traffic signal optimization plays a crucial role in improving the service ability of traffic networks in urban areas. With the traffic network getting more and more complex, there have been increasing research interests in employing intelligent algorithms to find proper settings for traffic signals. As a special type of evolutionary algorithms, estimation of distribution algorithms (EDAs) possess strong optimization ability but have seldom been used in traffic signal optimization. In this paper, two efficient variants of continuous EDAs, namely EDA with variance enlargement strategy ($EDA_{ve}$) and EDA with variable width histogram model (EDA-VWH), are modified and adopted as optimizers to find proper traffic signal cycles in an actual urban area with multiple intersections. The performances of the two resultant algorithms, i.e. modified EDAve ($mEDA_{ve}$) and modified EDA-VWH (mEDA-VWH), are comprehensively studied through a VISSIM-MATLAB integrated simulation platform, which could provide a convenient and close-to-reality simulation environment. The simulation results showed that $mEDA_{ve}$ and mEDA-VWH could effectively reduce the mean delay time of all vehicles under different traffic conditions. In comparison with four other algorithms, including genetic algorithm, particle swarm optimization, differential evolution and random search method, the two modified EDAs also achieved competitive results.

In the context of a rapid developing urban economy and the increasing number of motor vehicles, urban commuting transportation has witnessed a serious mismatch between the supply of and the demand for transportation network resources. In developing an urban multi-mode traffic network, using a urban traffic transfer hub to coordinate the transportation capabilities among different traffic networks is perceived to be highly effective for exploring the network transportation capacity of an entire transportation system, and improving travel efficiency and experiences for the public. Based on the super-network model, this paper develops a topological structure for a multi-mode traffic network, in which two typical combined travel modes are selected to establish the path impedance function for that network. Moreover, the multi-mode traffic allocation model and the solving algorithm are constructed in the research. The paper studies the impact of two types of factors related to the transfer capacity of passenger flows based on the regular traffic network of a bus-and-subway transfer hub using a sensitivity analysis of the transfer time and the associated penalty. The findings suggest that both changes in transfer walking time and the transfer penalty have no significant effect on the bus passenger flow.

This paper introduces a new methodology for reconstructing vehicle densities of freeway segments by utilizing the limited data collected by traffic-counting sensors and developing a macroscopic traffic stream model formulated as a switched reduced-order state observer design problem with unknown or partially known inputs. Specifically, the traffic network is modeled as a hybrid dynamic system in a state space that incorporates unknown inputs. For freeway segments with traffic-counting sensors installed, vehicle densities are directly computed using field traffic count data. A reduced-order state observer is designed to analyze traffic state transitions for freeway segments without field traffic count data to indirectly estimate the vehicle densities for each freeway segment. A simulation-based experiment is performed applying the methodology and using data of a segment of Beijing Jingtong freeway in Beijing, China. The model execution results are compared with the field data associated with the same freeway segment, and highly consistent results are achieved. The proposed methodology is expected to be adopted by traffic engineers to evaluate freeway operations and develop effective management strategies.

In this paper we present DALI, a distributed, collaborative multi-agent traffic signal timing system (TST) for highly dynamic traffic conditions. In DALI, intersection controllers are augmented with software agents which collaboratively adapt signal timings by considering the feedback of all controller agents that may be affected by a change. The model is based on a real-world TST and will be deployed with minimal changes to the infrastructure. DALI has been validated by traffic engineers as well as through extensive simulation of the City of Richardson’s traffic network, comprising 128 signalized intersections. The experimental results show that, in highly dynamic scenarios, DALI outperforms the conventional traffic system used by the city as well as a state-of-the-art reinforcement learning-based TST.

Traffic accidents seriously threaten people’s lives and property all over the world. Therefore, it is of great significance to human society to have a long-term traffic accidents data with detail temporal and geographic information in a specific space, which can be used for traffic accident hotspots identification to reduce the incidence of traffic accidents. Here, we obtain a one-year dataset of traffic accidents of the city center in Changchun, Northeast China, in 2017. In this paper, we analyze the risk of traffic accident in urban area, and then discover the characteristics of traffic accidents at the temporal and spatial aspect. We construct a traffic network, which takes crossings as nodes and road sections as edges and weighted by the total number of traffic accidents. In addition, we integrate road structure data and meteorological data to explore the characteristics of the traffic network.

We propose a dynamic combined-mode traffic network model considering transfer behaviors. We assume that travelers can be classified into two classes: one class is pure-mode travelers who complete a trip by single transportation mode, and another is combined-mode travelers who cover a journey by car, bus, and so forth. The multimode point queue model is used to model the interaction of cars and buses on the network. We present an integrated variational inequality formulation to capture the complex traveler choice behaviors such as departure time choices, transfer point, and route choices. Finally, a numerical example is given to illustrate the effectiveness of the proposed heuristic algorithm and model.