Complex Traffic Network Research Articles

Combining jumping knowledge into traffic forecasting: An attention-based spatial-temporal adaptive integration gated network

Traffic forecasting has become a core component of Intelligent Transportation Systems. However, accurate traffic forecasting is very challenging, caused by the complex traffic road networks. Most existing forecasting methods do not fully consider the topological structure information of road networks, making it difficult to extract accurate spatial features. In addition, spatial and temporal features have different impacts on traffic conditions, but the existing studies ignore the distribution of spatial-temporal features in traffic regions. To address these limitations, we propose a novel graph neural network architecture named Attention-based Spatial-Temporal Adaptive Integration Gated Network (AST-AIGN). The originality of AST-AIGN is to obtain a spatial feature that more accurately reflects the topological structure of the road networks by embedding Graph Attention Network (GAT) into Jumping Knowledge Net (JK-Net). We propose a data-dependent function called spatial-temporal adaptive integration gate to process the diversity of feature distribution and highlight features in road networks that significantly affects traffic conditions. We evaluate our model on two real-world traffic datasets from the Caltrans Performance Measurement System (PEMS04 and PEMS08), and the extensive experimental results demonstrate the proposed AST-AIGN architecture outperforms other baselines.

The Association between Rainfall and Taxi Travel Activities: A Case Study from Wuhan, China

Rainfall has a significant impact on urban population mobility, posing great challenges to traffic management and urban planning. An understanding of this influence from multiple perspectives is urgently needed. In this study, we devised a multiscale comparative research framework to explore the spatiotemporal effects of rainfall on taxi travel patterns, aiming to provide a new perspective on the investigation of rainfall’s impact on urban human mobility. More specifically, at the macroscopic scale, we computed taxi travel indicators across the entire study area and used kernel density estimates to observe the spatiotemporal distribution patterns influenced by rainfall. Subsequently, complex traffic networks were constructed by considering urban road intersections as nodes and combined with visualization methods to understand changes in taxi travel patterns visually at the microscopic level. We selected Wuhan City, a typical urban area in southern China with frequent rainfall, as the study area and used meteorological data along with a large volume of taxi spatiotemporal trajectory data for investigation. Results indicated a 4.16% decrease in weekly travel volume due to rainfall, with a 3.96% decrease on workdays and a 4.64% decrease on weekends. However, nighttime rainfall between 19:00 and 22:00 on weekdays increased the demand for taxi travel. Furthermore, the impact of rainfall on weekends exceeded that on workdays, restricting people’s mobility and leisure activities, resulting in reduced travel to recreational tourist spots and commercial pedestrian streets. Rainfall altered residents’ travel preferences to some extent, with more residents choosing taxis during rainy weather, which led to decreased transportation efficiency and increased traffic congestion. These findings contribute to a deeper understanding of the complex relationship between population mobility patterns and the urban ecological environment, providing valuable insights for planning resident travel and taxi dispatching under adverse weather conditions.

Low-Carbon Mixed Traffic Route Recommendation for Community Residents Based on Multilayer Complex Traffic Network

With the proposed “carbon peaking” and “carbon neutral” goals in China, the transportation sector, as the second largest consumer of oil and a major producer of greenhouse gases, is a critical area for energy efficiency and emission reduction actions. However, few studies have focused on the effective combination of solving residents' commuting challenges and low-carbon travel. In this paper, by extracting real traffic flow data from taxi and bike-sharing trajectory data, a multilayer complex traffic network is formed to realize an interactive visual exploration of urban traffic patterns. Based on this network a low-carbon travel route recommendation is implemented using a modified genetic algorithm to reduce personal carbon emission and travel costs. Meanwhile, the trip chain level carbon emission estimation method is defined for city streets and recommended routes. With the integration of the above algorithms, a visual analytics system is designed and implemented to support the joint exploration of urban traffic patterns and the street carbon emission distribution, low-carbon mixed traffic route recommendations for inter-community commuting, and optimization of low-carbon recommended routes by adjusting bike stations. Take the taxi and bike-sharing trajectory data in Xiamen, China as an example, an evaluation analysis of the system shows that the method is effective in reducing commuting costs for community residents while reducing personal travel carbon emission.

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system.

Bifurcation Analysis of Driver's Characteristics in Car-Following Model

Abstract According to traffic flow theory, traffic is affected not only by road conditions such as bottlenecks, the environment, interruptions, and so on but also by the driver's behavior. To control and manage increasingly complex traffic networks, it also becomes necessary to study the effects of driver characteristics significantly. In this research, a novel car-following model is proposed which considers both the driver's cautious and aggressive instincts for optimal and relative velocity integrals. To analyze the stability of the new model, a small perturbation method was used. Further, the modified Korteweg–de-Vries equations were established with the help of a reductive perturbation method. In bifurcation analysis, we examine the existence and stability of Hopf bifurcation in various systems. This helps to gain deeper insight into the behavior of these dynamical systems and can be used to develop more efficient control strategies. Numerical simulations and theoretical analyses both show that the aspects of the enhanced model related to driver characteristics have a major affect on traffic flow stability. Additionally, the model can adeptly handle traffic congestion and quickly return to its normal state if any disruption occurs.

Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting

AbstractTraffic prediction is an important part of intelligent transportation system. Recently, graph convolution network (GCN) is introduced for traffic flow forecasting and achieves good performance due to its superiority of representing the graph traffic road structure network. Moreover, the dynamic GCN is put forward to model the temporal property of the traffic flow. Although great progress has been made, most GCN based traffic flow forecasting methods utilize a single graph for convolution, which is considered not enough to reveal the inherent property of traffic graph as it is influenced by many factors, for example weather, season and traffic accidents etc. In this paper, an exotic graph transformer based dynamic multiple graph convolution networks (GTDMGCN) is conceived for traffic flow forecasting. Instead of the single graph, multiple graphs are constructed to modulate the complex traffic network by the proposed graph transformer network. Additionally, a temporal gate convolution is proposed to get the temporal property of traffic flow. The proposed GTDMGCN model is evaluated on four real traffic datasets of PEMS03, PEMS04, PEMS07, PEMS08, and there are average increments of 9.78%, 7.80%, 5.96% under MAE, RMSE, and MAPE metrics compared with the current results.

Design of Fuzzy and Conventional Controllers for Modeling and Simulation of Urban Traffic Light System with Feedback Control

Traffic patterns in urban areas present a complex and dynamic system that is characterized by inherent uncertainties. The presented study is a traffic light control system with feedback. The controller of the system is designed in a fuzzy and conventional way and is applied to a network of two junctions. The verification is performed using the MATLAB fuzzy toolbox platform (for designing the fuzzy controller) and Aimsun platform for microsimulation of the two junctions using the two types of controllers. To accomplish the control of the system a fuzzy controller on heuristic rules proposed to allow adaptive traffic control on signalized junctions in urban environments. The Fuzzy Toolbox in MATLAB is used to simulate the fuzzy controller. The Aimsun traffic simulator is used to model and simulate a traffic network of two intersections. The green light duration in the Aimsun model is based on the results for the two controllers from two separated experiments. Simulations of Aimsun models with the two types of controllers, the fuzzy and the conventional one, are compared. The experiment is performed under the premise that the traffic flow is oversaturated. Findings show that in a network of two junctions both controllers perform in a similar manner for the first junction. However, for the second junction, the fuzzy controller tends to have some advantages over the conventional controller with regard to higher traffic flow. In conclusion, the overall performance of the fuzzy controller is better than the one of the conventional controller, but further research is needed for more complex traffic networks.

Algorithms for the Pareto solution of the multicriteria traffic equilibrium problem with capacity constraints of arcs

<p style='text-indent:20px;'>We focus on the multicriteria traffic equilibrium problem with capacity constraints of arcs. First, we generalize Beckmann's formula to deal with multicriteria traffic equilibrium problems with capacity constraints of arcs and prove that the solution of the mathematical programming problem is a Pareto traffic equilibrium flow with capacity constraints of arcs. Furthermore, we present a restricted algorithm for computing the Pareto traffic equilibrium flow with capacity constraints of arcs. Using the restricted algorithm, one does not need to know the set of available paths joining origin-destination pairs. This proves very helpful for complex traffic networks. Finally, for the algorithms of the Pareto traffic equilibrium flow, we give two examples to exemplify calculation processes.</p>

HMIAN: A Hierarchical Mapping and Interactive Attention Data Fusion Network for Traffic Forecasting

With the development of intelligent transportation system (ITS), the vital technology of ITS, short-term traffic forecasting, gains increasing attention. However, the existing prediction models ignore the impact of urban functional zones (FZs) on traffic data, resulting in inaccurate extractions of dynamic spatial relationships from network. Furthermore, how to calculate the influence of external factors, such as weather and holidays on traffic is an unsolved problem. This article proposes a spatio-temporal hierarchical mapping and interactive attention network (HMIAN), which extracts the spatial features from traffic network by constructing FZs, and designs an effective external factors fusion method. HMIAN uses the hierarchical mapping structure to aggregate the roads into FZs, calculate the interaction between FZs and feed this information back to the spatial features. And the interactive attention mechanism is utilized to fuse the traffic data with external factors effectively, and extracts temporal features. In addition, some experiments were carried out on three real traffic data sets. First, experiment results show the better prediction performance of the proposed model compared with other existing methods in a complex traffic network. Second, the longitudinal comparison experiment verifies that the hierarchical mapping structure is effective in extracting spatial features in a complex road network. Finally, the influence of different external factors and fusion methods on traffic prediction are compared, which provides a consult for subsequent research on the influence of external factors.

PF‐ITS: Intelligent traffic service recommendation based on DeepAFM model

Due to the progressive complexity of traffic networks, the traffic pressure increases sharply and traffic accidents occur frequently, which is largely posed by imprecise traffic information service provided in existing Intelligent traffic service systems (ITSSs). To relieve traffic information trek encountered in complex traffic networks, the personalized traffic information recommendation based on click through rate (CTR) prediction has attracted extensive attention. However, the data sparsity and cold start problems in traditional recommendations hinder their real-time applications in ITSSs. In this paper, the multisource data with different types of context information are utilized to construct a personalized fine-grained recommendation method for intelligent traffic services (PF-ITS), which includes three components: a road condition optimization strategy (RCOS) to capture users' behavior preferences and traffic patterns, an encoder–decoder long short-term memory (LSTM) model to address the data sparsity and cold start problems with rich context information, and an improved DeepFM model based on attention mechanism (DeepAFM) to exert personalized fine-grained traffic information recommendation with embeddings of multisource data. More specifically, the RCOS is proposed to perform coarse-grained route recommendation based on path planning theory, in which the traffic data and drivers' preferences are fully utilized for comprehensive modeling. The encoder–decoder LSTM model is employed for representation learning, in which the traffic sequences and driving behaviors are mapped into dense distributed representations with rich semantic information. The DeepAFM is utilized to achieve effective driving safety guarantee according to an individual's requirements, in which the weighted low-order feature combinations and high-order feature interactions are incorporated for personalized fine-grained recommendation. We also conduct extensive experiments on public data sets and in real-world scenarios. The experimental results demonstrate that the PF-ITS method based on RCOS and DeepAFM outperforms the state-of-the-art baseline models in effectiveness and efficiency.

Complex Traffic Network Analysis Method Based on a Multiscale Aggregation Model

Identifying the aggregation characteristics of the geospatial network is an important aspect of analyzing highway traffic networks. Based on the complex network theory, this paper studies the block aggregation characteristics of the highway traffic network and proposes an Improved PageRank Spectral Clustering (IPSC) Algorithm to divide the functional blocks of highway traffic networks. Firstly, the theoretical model of a highway traffic network is constructed by adding location attribute weight, geographical distance weight, road grade weight, and dynamic traffic congestion weight. Secondly, the improved PageRank algorithm is used to get the ranking of key nodes of the highway traffic network. The clustering center and the number of clusters are determined by the ranking of key nodes and the shortest path distance. Then the improved spectral clustering algorithm is used to divide the functional blocks of the highway transportation network and identify the special common blocks of the highway transportation network. Finally, the IPSC Algorithm is used to analyze the aggregation mode of complex traffic networks at city and district scales. Crossing the limit of administrative division, the division results of special common blocks of highway transportation networks are obtained. Maintaining the connectivity between blocks can improve the overall efficiency of highway transportation networks.

Two-Stage Vehicle Routing Optimization for Logistics Distribution Based on HSA-HGBS Algorithm

Aiming at the problems of complex urban road network, low efficiency of logistics distribution, and the difficulty of large-scale logistics distribution area division and routing planning, this paper proposes a two-stage logistics distribution vehicle routing optimization (VRP) method based on the establishment of a multi-factor complex road network constrained logistics distribution mathematical model. Considering the complex traffic elements and road network topological structure in logistics and distribution, in the first stage, a heuristic simulated annealing (HSA) distribution region partitioning algorithm is proposed with the objective of balancing vehicle task load to divide the urban logistics distribution network under complex road networks, so as to reduce the area scale and path search cost. In the second stage of route decision making, aiming at minimizing the total cost of logistics distribution, combining the VRP problem with complex road network conditions, a heuristic path search method combined with complex road network model constraints is proposed. In this stage, a hybrid genetic beam search(HGBS) algorithm is used to plan the path nodes, reduce the randomness of the model in the initial search for paths by heuristic genetic algorithms, then combine with Beam graph search methods to reduce the space and time used for the search, and use optimization algorithms to improve the accuracy of independent sub-region routing optimization and the rationality of overall physical distribution route selection. Finally, the proposed method is validated in this paper with two practical cases. The experimental results show that the two-stage decision-making algorithm proposed in this paper has certain advantages in partitioning schemes, minimizing total cost and iteration times. Through comparison, the optimization ability of this method for logistics distribution networks is proved.

Short-Term Traffic State Prediction Based on Mobile Edge Computing in V2X Communication

Real-time and reliable short-term traffic state prediction is one of the most critical technologies in intelligent transportation systems (ITS). However, the traffic state is generally perceived by single sensor in existing studies, which is difficult to satisfy the requirement of real-time prediction in complex traffic networks. In this paper, a short-term traffic prediction model based on complex neural network is proposed under the environment of vehicle-to-everything (V2X) communication systems. Firstly, a traffic perception system of multi-source sensors based on V2X communication is proposed and designed. A mobile edge computing (MEC)-assisted architecture is then introduced in a V2X network to facilitate perceptual and computational abilities of the system. Moreover, the graph convolutional network (GCN), the gated recurrent unit (GRU), and the soft-attention mechanism are combined to extract spatiotemporal features of traffic state and integrate them for future prediction. Finally, an intelligent roadside test platform is demonstrated for perception and computation of real-time traffic state. The comparison experiments show that the proposed method can significantly improve the prediction accuracy by comparing with the existing neural network models, which consider one of the spatiotemporal features. In particular, for comparison results of the traffic state prediction and the error value of root mean squared error (RMSE) is reduced by 39.53%, which is the greatest reduction in error occurrences by comparing with the GCN and GRU models in 5, 10, 15 and 30 min respectively.

Applying the Virtual Input-Output Method to the Identification of Key Nodes in Busy Traffic Network

How to identify the key nodes effectively in urban traffic networks to achieve the equitable resource allocation face to the complex traffic network? This issue needs to be solved in current traffic management. This study considered the urban traffic network topology and network traffic status, put forward an improved model based on the economics of the input-output method by introducing a virtual node to the selected network set up with the flow of urban traffic network, sensor nodes by Leontief inverse matrix calculation coefficient to determine node importance, according to the node importance to deliberate attack traffic network to analyze its robustness, to test the accuracy and practicability of the method. The results show that this improved method adopted to measure the importance of traffic nodes from the global scope has the advantages of fast calculation and simple process and provides a more reliable basis for rational allocation of transport resources.

Geometrical risk evaluation of the collisions between ships and offshore installations using rule-based Bayesian reasoning

Increasing human installations and vessel traffic in offshore waters render a collision risk between ships and offshore installations (SOI). Past decades have witnessed many accidents occurred in the offshore waters involving complex traffic networks. To safeguard offshore installations and improve water-bound transport safety, this paper proposes a novel Bayesian-based model to assess the SOI collision risk involving passing ships. It first identifies the relevant risk factors with the aid of a geometrical analysis concerning SOI collisions. The causal relationships between the risk factors are numerically defined by causal rules with a degree of belief structure, while a Bayesian network (BN) is constructed to aggregate the evaluated value of each risk factor and to assess the collision risks involving different navigational environments. To illustrate the new model, a real case on SOI collision risk in the Liverpool Burbo Bank offshore wind farm is investigated. The results provide empirical evidence for SOI collision risk analysis under complex water conditions and uncertain navigational environments and hence useful insights on SOI collision avoidance.

On finding optimum commuting path in a road network: A computational approach for smart city traveling

AbstractCommuting in big cities with heavy traffic is a real‐world task faced by many on a daily basis. Finding a suitable path for commuting in real‐life complex traffic networks is an important research problem with many applications. The existing work in this domain is based on the travel time and distance from source to destination. However, other than these two factors, there are many additional features that impact the overall travel time and its quality. Some of these additional features include environmental factors, road condition, and the traffic flow. The driving time can be minimized by selecting the most suitable path where there is less congestion and other travel related conditions are favorable. Commuting duration can increase even on the shortest path if there is congestion or the route is blocked. This work presents a mobile crowdsourcing‐based model to find suitable commuting path(s) by considering the factors that directly or indirectly influence the overall travel time. Experiment in this work refers the naturalistic driving study to select the travel related features. An algorithm is proposed to find the suitable path from the user provided source to the destination using crowdsourced data generated using mobile application. Unlike other algorithms, the proposed approach can address the network peculiarities where travel cost is not only based on the distance between the nodes but other indirect factors are also involved. This work extracts all possible paths from a source to the destination and then computes the travel cost in terms of distance and satellite factors across the paths. This proposal is evaluated on eight large real‐world road network data sets. A comparison is performed with four state‐of‐the‐art pathfinding methods. These include, Floyd‐Warshall algorithm, Bellman‐Ford algorithm, open shortest path first algorithm, and Dijkstra algorithm. Empirical analysis shows that the additional factors incorporated in the proposed mobile crowdsourcing model while finding a suitable path have a significant impact on the travel time. The results show better performance of the proposed model than its counterparts.

Estimating probability distributions of travel demand on a congested network

We aim to infer the probability density function (pdf) of Origin–Destination (O–D) demand variables using multiple sets of traffic counts over a network. Through integrating statistics and optimization techniques with transportation domain knowledge, we propose an estimation framework based on Generalized Method of Moment (GMM) with both options of exact and approximated estimators. Compared with existing methods for day-to-day O–D matrix estimation, our approach has three unique advantages. First, it is a rigorous statistical method with a capability of incorporating complex traffic network models suitable for a congested network. Second, our estimation framework is flexible to handle a wide variety of probabilistic models. Finally, instead of just providing point estimates, it reveals large sample statistical properties of the proposed estimator, which serve as a theoretical foundation for assessing estimation quality, constructing confidence region and testing model adequacy. Three numerical examples of different scales are accompanied to demonstrate various aspects of the proposed estimation framework.

Research on Mixed User Equilibrium Model Based on Mobile Internet Traffic Information Service

Previous studies established traffic demand equilibrium with an assumption that all the traffic information on road is easily accessed by the in-need traffic participants, which is not true in the real applications (due to data collections difficulty). The newly emerging smart portable devices (e.g., smart phones) generate massive on-site traffic data (speed, density, etc.), which stimulates us re-consider designing the traffic demand equilibrium. For the purpose of analyzing mobile internet service influence on traffic demand, we build up a Probit-based model with consideration of multiple traffic constraints (i.e., traveler type, actual travelling time, perceiving travelling time). The Monte Carlo method is introduced to simulating initial route selection probability distributions, and the Method of Successive Averages (MSA) is developed to help the Monte Carlo algorithm converge at optimal solution. We have implemented our model on typical traffic travelling scenario with very complex traffic network demands. The experimental results suggested that larger mobility service coverage can significantly reduce the overall traffic time in the free flow state, and the mobility service coverage rate ranging from 0.6 to 0.8 is supposed to provide minimum travelling time for the overall traffic network, while larger coverage rate at congested state may reduce the traffic network efficiency.

An optimized IS-APCPSO algorithm for large scale complex traffic network

Chaotic particle swarm optimization algorithm is improved by incorporating antibody concentration, adaptive propagation, optimization mechanism of the multi-population evolution strategy, elite particles chaotic traversal mechanism and constraint processing mechanism. In this paper, an improved adaptive propagation chaotic particle swarm optimization algorithm based on immune selection (IS-APCPSO algorithm for short) is proposed. The performance of several algorithms has been compared by multimodal function, functions with high dimensional and complex constraints, bi-level programming function and a classic example of traffic network optimization. The experimental results prove that the proposed algorithm in accelerating convergence rate, increasing the diversity of particles, and preventing premature phenomenon is effective. The novel algorithm is expected to be used in the model solution of large-scale complex traffic network optimization problem.

Research and Application of the Optimal Repair Path Based on BP-Dijkstra in the Distribution Network

The existing power system emergency repair system mainly relies on manual scheduling and selection of traffic paths based on experiences. Also, the existing traffic navigation has only one-time route planning, which may not be intelligent enough to fit the traffic changes. In order to solve the above problems, this paper establishes a power emergency repair system based on GPRS wireless communication technology, on-board GPS terminal equipment, transportation and power system GIS. Based on the current traffic information, BP neural network is used to predict the average speed of different paths and to calculate the running time of each path. The Dijkstra algorithm was introduced in the later stage to find the optimal repair path with the shortest time duration. The updates of time settings during optimization are introduced. The original optimal repair path is maintained within the set time limits; otherwise the new path will be updated. In this paper, a complex traffic network analysis and simulation verification are presented. The results show that the algorithm is feasible and applicable.