Traffic Flow Characteristics Research Articles

Multi-View Multi-Attention Graph Neural Network for Traffic Flow Forecasting

The key to intelligent traffic control and guidance lies in accurate prediction of traffic flow. Since traffic flow data is nonlinear, complex, and dynamic, in order to overcome these issues, graph neural network techniques are employed to address these challenges. For this reason, we propose a deep-learning architecture called AMGC-AT and apply it to a real passenger flow dataset of the Hangzhou metro for evaluation. Based on a priori knowledge, we set up multi-view graphs to express the static feature similarity of each station in the metro network, such as geographic location and zone function, which are then input to the multi-graph neural network with the goal of extracting and aggregating features in order to realize the complex spatial dependence of each station’s passenger flow. Furthermore, based on periodic features of historical traffic flows, we categorize the flow data into three time patterns. Specifically, we propose two different self-attention mechanisms to fuse high-order spatiotemporal features of traffic flow. The final step is to integrate the two modules and obtain the output results using a gated convolution and a fully connected neural network. The experimental results show that the proposed model has better performance than eight other baseline models at 10 min, 15 min and 30 min time intervals.

An Improved Cellular Automata Traffic Flow Model Considering Driving Styles

An improved cellular automata model (CA model) considering driving styles is proposed to analyze traffic flow characteristics and study traffic congestion’s dissipation mechanism. The data were taken from a particular case in the Next Generation Simulation (NGSIM) program, which selected US-101 as the survey location from 7:50 a.m.–8:05 a.m. to investigate vehicle trajectory information. Different driving styles and the differences in vehicle parameters (speed, acceleration, deceleration, etc.) were obtained using principal component analysis and the k-means clustering method. The selected model was proposed for improvement based on analyzing the existing CA models and combining them with the actual road conditions. Considerations of driving styles and two operation mechanisms (over-acceleration and speed adaptation) were introduced in the improved model. The result obtained after the traffic simulation shows that the improved CA model is effective, and the mutual transformation of different traffic flow phases can be simulated. In the improved CA model, dissipating traffic congestion effectively and balancing the overall flow of the road are realized to improve the traffic capacity up to around 115% compared to the NaSch model and meet the demand of all kinds of drivers expecting to drive at the safest distance, which provides a theoretical basis for relieving traffic congestion. The various driving styles in terms of safety, comfort, and effectiveness are performed differently in the improved CA model. An aggressive driving style contributes to increasing traffic capacity up to around 181% compared to a calm driving style, while the calm style contributes to maintaining traffic flow stability.

Accuracy verification of magnetic sensors in different weather conditions

An intelligent transport system cannot exist without high-quality information about transport. One of the possibilities for data collection is a sensory transport network. The city of Žilina has a wireless network of magnetic sensors built a few years ago. I continuously collect traffic information. It monitors all lanes in the direction to and from the city center. The sensors thus create an area bounded by virtual gates which count entering and exiting vehicles. The sensory network sends obtained data by each sensor to a publicly accessible database. This article also describes mentioned database that provides the traffic flow characteristics – intensity, speed, and classification of vehicles. The question of the magnetic sensors used is their accuracy. Their function is counting, speed measuring, and vehicle classification. Sensors detect all these characteristics based on the magnetic field changes by passing vehicles. In this paper, the authors verify the accuracy of the sensors in two traffic surveys in warm weather and winter conditions. In both surveys, certain deviations were evident, but they did not fundamentally affect the accuracy of vehicle counting.

Оценка эффективности спиралевидной разметки на кольцевых пересечениях автомобильных дорог

The results of a number of foreign studies recommend the application of spiral markings to ensure a higher level of safety at roundabouts of medium and large diameter highways. In a number of cities of the Russian Federation, these recommendations were implemented with the introduction of new traffic management schemes using spiral marking of traffic lanes. However, there is no objective data confirming the effectiveness of these measures in Russia. The aim of the study was to evaluate the effectiveness of spiral markings according to two criteria – the number of road accidents and traffic violations at roundabouts before and after the reorganization of traffic. The information was obtained from the traffic police and from video surveillance of individual sections of roundabouts. As a result of the study: 1) the hypothesis of a decrease in the number of accidents and the assertion that new traffic management schemes (spiral markings) by themselves provide greater traffic safety at roundabouts are refuted; 2) it is revealed that drivers tend to violate the requirements of spiral markings, which increases the likelihood of accidents; 3) it is concluded that new traffic management schemes can have a positive impact on road safety only when engineering measures are implemented to physically separate traffic flows on the ring roadway and reduce the speed of vehicles at the entrances and exits of roundabouts. The results of the work revealed promising areas for further research: to study the relationship between the trajectory of vehicles, their location from the point of view of certain intersection sites, spiral markings, characteristics of traffic flow (speed, density, congestion, flow composition), as well as weather condi¬tions. The identification of such links will allow us to evaluate the effectiveness of spiral marking and draw conclusions about the expediency of its further use at roundabouts in the territory of the Russian Federation.

Research on air pollution characteristics and planning strategy of urban street environment

Dense buildings in modern cities make street pollutants more and more difficult to disperse, and the exposure level of urban residents to pollutants has increased significantly. This study focuses on the spatial and temporal distribution of ambient air pollution in urban streets and the relationship between street morphology and pollutant dispersion, and explores ways to reduce ambient air pollution in streets through spatial design. The study used the CityGrid urban grid data monitoring station to conduct an empirical study on an urban trunk road in Wuhan during the winter of 2020 to 2021, monitoring pollutants including NO2, O3, PM2.5, and PM10. The results showed that pollutant concentration changes in the near-road environment are affected by a combination of meteorological elements and traffic flow characteristics. The wind parallel to the road is more favorable to evacuate pollutants inside the street canyon, and the ambient wind above the canyon perpendicular to the road causes vortices in the canyon that cause gaseous pollutants to accumulate on the leeward side of the canyon. The distribution of particulate pollutants is mainly related to the distance of road pollutant sources. Building access ventilation can effectively evacuate street pollutants, and NO2 and O3 decay to stable levels in shorter distance from the road than PM2.5 and PM10 in downwind direction. The future urban street planning can effectively alleviate street pollution levels through strategies such as street canyon morphology control, green landscape facilities arrangement, increasing the building interface opening, and building bottom overhead.

Definisanje dnevnih kapaciteta za potrebe planiranja puteva u Republici Srbiji

In every edition of the Highway Capacity Manual (HCM) until 2016, three levels of capacity analysis were defined: operational, project and planning analysis. The level of detail of each analysis is a function of purpose, breadth of access and available information. Planning analysis determines capacity in the earliest stages of planning, when small amount of data and information is available. The planning procedure is based on the AADT forecast and macro traffic simulation. Often, the usage of simulation models can lead to errors, and for these reasons, when analyzing traffic demands, it is necessary to carry out a check when more informations are available. Planning analyzes from the HCM manual are generally focused on broad issues such as initial problem identification, road design concept, and when alternatives are compared. These analyzes are suitable for evaluating proposed system measures, such as heavy vehicle lane usage control, highway ramp metering, and other applications of intelligent transportation systems. The methodology recommended in HCM implies the use of default input values, i.e. table of generalized values. Given that the recommended capacity values are based on typical road profiles and traffic flow characteristics in the USA, the paper provides a detailed capacity analysis at the planning level for local conditions - four standard geometric two-lane and highway profiles. Capacities are calculated for different values of design hourly volume, design speed, peak hour factor, commercial vehicle impact and terrain type, in order to compare with the generalized capacity tables from HCM2010. The comparative analysis indicates differences in the calculated capacity values, and for that reason the obtained values are recommended for use in model simulations for local conditions in the Republic of Serbia.

Traffic Flow Characteristics in Work Zone and Non-Work Zone Environment and Its Impact on Road Crashes at the Segment Level

Traffic Flow Characteristics in Work Zone and Non-Work Zone Environment and Its Impact on Road Crashes at the Segment Level

ПРЕДИКАТИВНЫЙ ПОДХОД К АНАЛИЗУ КОНФЛИКТНОСТИ В ТРАНСПОРТНОМ ПОТОКЕ

The paper considers the concept of conflict in the traffic flow as a chain of phenomena that collectively increase the likelihood of an accident. Statistical indicators of the accident rate among various classes of vehicles, as well as indicators of environmental parameters and traffic flow characteristics were taken as initial data. The developed model can be used as the first link in the training of artificial intelligence systems for high-quality monitoring and management decision-making in the field of transport coordination and general regulation.

Влияние параметров транспортного потока и характеристик дорог на безопасность дорожного движения

Despite the positive effect of the implementation of existing federal targeted programs and national projects in the field of road safety (RTS), the death rate on roads remains quite high. The article considers the current state of accidents, the dynamics of the development of the road network and the level of motorization over the past 10 years. The factors that determine the current state of accidents are identified. Based on the accident rate on the territory of the Krasnoyarsk Territory, it was revealed that the most serious road traffic accidents (RTA) occur on roads outside the city limits, a large percentage of accidents involving vehicles of categories M2, M3 and N. Based on the analysis of studies in the field of road safety assessment and statistical data, the purpose of the study is defined - to identify the impact of traffic flow parameters and road characteristics on road safety. The paper uses the methods of mathematical statistics, the content of which was determined in the course of a study of 20 sites on the FAD in the Krasnoyarsk Territory. For analysis, sections were selected that differ in the level of accidents, traffic flow characteristics and geometric parameters. As a result of a scientific study, it is mathematically confirmed that traffic safety is influenced by the composition of the traffic flow and the variational range of speeds between the overtaken and overtaking vehicles. The dependence of the variational range of speeds between the overtaken and overtaking vehicles on the composition of the traffic flow, the dependence of the partial accident rate coefficient K11 on the variational range of speeds between the overtaken and overtaking vehicles are determined. A regression model has been obtained for the dependence of the average annual number of accidents on the width of the shoulder, the radius of the curve in plan, visibility, the distance from the edge of the carriageway to a cliff with a depth of more than 5 m, the friction coefficient, the composition of the traffic flow, the variation range of speeds between the overtaken and overtaking vehicles. The scientific novelty of the study is the dependence of the average annual number of accidents on the traffic flow parameters and road characteristics. The practical significance of the study lies in the increase in traffic safety due to the use of the final accident rate method in its assessment, which takes into account the composition of the traffic flow and the variational range of speeds between the overtaken and overtaken vehicles. Further research is aimed at identifying yet unaccounted for factors influencing RTS.

Noise pollution of the road network of the city by road transport

The article is devoted to the analysis of noise pollution of a residential area by road traffic. It is noted that car noise is a great danger to human health, especially in large cities and industrial centers. Field studies of the noise characteristics of traffic flows in busy, dangerous sections of the road network of a large city have been carried out. It is shown that the level of car noise exceeds the maximum permissible sound level for any measured value of the flow intensity and distance from the road up to 35 m. The dependence of noise on the parameters of traffic flows is studied, analytical dependences are obtained, and correlation and regression analyzes are carried out. Measures have been proposed to reduce the level of automobile noise in busy sections of the road network of a large city.

Evaluation of the traffic flow characteristics in relation to the platoon occurrences

Traffic congestion has become part of daily life. Morning and afternoon queues have a major impact on increasing the average travel time. Furthermore, increasing the negative impact on the environment reduces the overall satisfaction of the public. Exceeding the maximum capacity of the road significantly reduces the speed and traffic flow. In the worst case, it can stop the traffic itself. The relationship between volume, speed, and density, is commonly expressed by Greenshield's fundamental diagrams. With their help, it is possible to determine the optimal intensity for a specific section of the road. The article deals with the evaluation and analysis of a congestion queue, called a platoon, on a specific section of road I/18 Strečno – Dubná Skala. As part of the study, a traffic analysis using radar was carried out. The interrelationships between the speed of the traffic flow and the formation of the platoon were analyzed from the data based on the measurement results. The results show significant changes in the speed of the traffic flow. Despite the almost constant intensity, a different state of formation of the platoon was recorded. The results are presented by graphical analysis of the values of frequency of occurrence of the platoon in all measured 15-minute intervals with graphical analysis of speed. In the next part, the research will deal with the composition of the traffic flow, direction, and gradient of the route.

Speed data collection methods: a review

Various studies have been focusing on a wide range of techniques to detect traffic flow characteristics, like speed and travel times. Therefore, a key aspect to obtain statistically significant set of data is to observe and record driver behaviours in real world.To collect traffic data, traditional methods of traffic measurement – such as detection stations, radar guns or video cameras – have been used over the years. Other innovative methods refer to probe vehicles equipped with GPS devices and/or cameras, which allow continuous surveys along the entire road route.While point-based devices provide information of the entire flow, just in the section in which they are installed and only in the time domain, probe vehicles data are referred both to temporal and space domains but ignore traffic conditions. Obviously, it is necessary that the data collected refer to representative samples, by number and composition, of the user population.The paper proposes a review of the most used methods for speed data collection, highlighting the advantages and disadvantages of each experimental approach. Accordingly, the comparison illustrates the best relief method to be adopted depending on the research and investigation that will be performed.

Statistical processing of traffic flow characteristics data

In the course of statistical processing of traffic flows characteristics data, the check for the presence of anomalous measurements in the sampling should be done at the very start of processing. If anomalous measurements are detected, they should be excluded from the sampling at an early stage of the processing and not taken into considerations in further calculations. Numerous criteria have been developed to detect outliers, their effectiveness depends on the sample size. In practice, for technical and economic reasons, it is impractical to obtain a large number of measurements, as a rule the sampling should be processed on the basis of limited number of observations. In this regard, methods for detection of outliers with a small number of measurements, which include the method based on the use of the Romanovsky criterion, are of great importance. However, the analysis of literary references showed that in some recently published studies it is not recommended to use the Romanovsky criterion with the number of measurements less than 20. Therefore, the purpose of this study is to test the power of the Romanovsky criterion (test) for a small number of measurements and the possibility of its application in samplings of small size (n≤ 20). The conducted studies have shown that the power of the Romanovsky criterion is quite high and it has high reliability with a small number of measurements, which makes it possible to use it in small samples to detect anomalous measurements.

Analysis of Traffic Noise Pollution Using Siemens Tecnomatix Plant Simulation

This paper considers a simulation-based tool for the prediction of roadside noise pollution. A special feature of the tool is that its core is a standard manufacturing simulation software – Tecnomatix Plant Simulation by Siemens. The tool uses standard elementary object classes of Plant Simulation such as path, vehicle, method etc., and provides a powerful and highly parameterisable environment for analysing the noise pollution by traffic flows. It possesses a high flexibility of model programming and is open for extensions and adjustments to new calculation methods. The infrastructure modeling facilities are essentially independent of the noise computation algorithms and thus can be used with various tool-internal or external numerical calculation components. As a result of earlier computational studies, a set of functional interdependencies of flow parameters and model settings have been obtained, and methods for calculating noise indicators have been adapted for their implementation in embedded languages of simulation tools. As a result of the programming-experimental study, a "Traffic Noise Tool" (TNT) software module has been developed. TNT allows to analyse the impact of traffic flow characteristics (traffic intensity, traffic flow by vehicle categories, and traffic mode in each track etc.) and of road infrastructure (number and carrying capacity of the cracks, additional distance between opposite directions, availability of noise protection devices, etc.) on the noise pollution of the roadside environment. During the simulation&calculation process, the noise characteristics of the individual vehicles are recorded and displayed by diagrams, and so is the equivalent overall noise level at a given monitoring point. The results of this study can be used in the practice.

Capacity Analysis Based on Vehicle Trajectory Data on a Weaving Bottleneck in Nanjing

This paper investigates the capacity of weaving bottlenecks in Nanjing, where multiple traffic streams merge or diverge closely, causing significant traffic disruptions. Utilizing trajectory data from 862 vehicles collected through UAV cameras, the study assesses the bottleneck's capacity and performance measures, including traffic flow, speed, and lane occupancy. The analysis employs a combination of the Highway Capacity Manual (HCM) 2010 guidelines and PTV Vissim simulation software. The HCM 2010 framework provides a standardized approach for evaluating traffic flow characteristics and determining the level of service, while Vissim allows for the evaluation of diverse traffic scenarios. The results reveal that the bottleneck operates at Level of Service E (LOS E), characterized by high congestion, reduced speeds, and prolonged travel times. However, introducing ramp metering to the area improves conditions, resulting in a transition to Level of Service D (LOS D). This study emphasizes the potential of ramp metering to enhance bottleneck performance. Nevertheless, future research should explore other strategies, such as intelligent transportation systems and improved public transportation services, to encourage modal shifts and reduce private vehicle usage. By addressing these challenges, cities like Nanjing can mitigate traffic congestion and create more efficient and sustainable transportation systems. The findings provide valuable insights for urban planners and policymakers seeking evidence-based solutions to optimize traffic flow and mobility in busy cities. By adopting the HCM 2010 guidelines and simulation tools like Vissim, this study contributes to the development of efficient traffic management strategies, ultimately fostering more livable and accessible urban environments.

Analysis of the impact of maximum platoon size of CAVs on mixed traffic flow: An analytical and simulation method

This paper analyzes the characteristics of mixed traffic flow with maximum platoon size of connected automated vehicles (CAVs) based on analytical and simulation methods. First, we discuss the car-following and headway types of mixed traffic flows with human-driven vehicles (HDVs), connected human-driven vehicles (CHVs), automated vehicles (AVs), and CAVs. Second, the probability distribution of the CAVs platoon size is derived based on the Markov chain model. Subsequently, the capacity model and stability condition of mixed traffic flow are proposed based on the probability distribution of the CAVs platoon size, and some characteristics of the influence of the maximum platoon size on traffic capacity and stability are analyzed. A numerical experiment based on car-following models was conducted to investigate the effect of the maximum platoon size on capacity, stability, safety, fuel consumption, and emission of mixed traffic flow. The results show that (1) the capacity of mixed traffic flow increases with the maximum platoon size of CAVs; (2) the stability of mixed traffic flow deteriorates with the increase in the maximum platoon size of CAVs; (3) the safety risk of vehicles in mixed traffic flow increases with the maximum platoon size of CAVs; (4) the fuel consumption and emissions (e.g., CO, HC, and NOx) increase with the maximum platoon size of CAVs. This indicates that the larger maximum platoon size can only improve traffic capacity, which is not conducive to the stability, safety, fuel consumption, and emissions of mixed traffic flow.

MS-ResCnet: A combined spatiotemporal modeling and multi-scale fusion network for taxi demand prediction

As an important part of urban intelligent transportation system, predicting users’ demand for taxi using offline GPS data has attracted interests in recent years. In general, the distribution of traffic flow in different areas of the urban is different. Furthermore, the characteristics of traffic flow in different location areas present different. Therefore, it is challenging to achieve accurate prediction of users’ demand for taxi in different spatiotemporal scenes. This paper presents a combined multi-scale residual calibration network (MS-ResCnet) using residual calibration network and multi-scale fusion mechanism to predict users’ demand for taxi. Specifically, mapping rasterization and time series division methods are used to convert vehicular GPS data into spatiotemporal images of traffic flow within continuous sub grid areas. Then, the proximity, periodicity, and tendency, as significant characteristics of spatiotemporal images of traffic flow in each sub grid area are extracted. Thus, we establish a multi-dimensional spatiotemporal characteristic perception scheme of traffic flow in each grid area. Moreover, the datum characteristics and calibration characteristics of spatiotemporal images are extracted through the dual channel ResCnet network. Through the deep stagger training network, the full fusion of multi-scale spatiotemporal characteristics is realized. The performance of MS-ResCnet model is evaluated and verified using public datasets. The simulation results show that the traffic flow prediction performance of MS-ResCnet model is better than that of traditional STAR model. The root mean square error (RMSE) of the proposed method outperform the STAR model around 2.57%.

Effect of Bottle Neck On Speed (Road N Waena – Abepura City Jayapura)

The characteristics of traffic flow are divided into 3 parts, namely volume (flow), speed (speed), and density (density) where the three have a fundamental relationship that is used as a guide to determine the mathematical value of road capacity for ideal conditions. By using the relationship between volume, speed, and traffic density, it can be seen the results of the flow and speed on the road section if congestion occurs. The location is on the Abepura – Sentani highway where on this road there is a phenomenon of narrowing of the road lane which is right in front of JNE Padang Bulan. There are 2 types of roads in the study location, namely 4 lanes 2 directions and 2 lanes 2 directions. A model of the relationship between speed and distance before and after the bottle neck point was obtained at the study location, namely on the Waena - Abepuea road section, Jayapura City in three conditions

Full-time scale resilience enhancement strategies for an integrated electricity-gas-transportation coupled system

The frequent occurrence of extreme disaster events with low probability and high risk poses a serious threat to the safe and stable operation of power grids. With the development of energy internet technology, the deep integration of power distribution, natural gas and transportation networks has opened a promising way for resilient distribution networks. This paper proposes a full-time scale resilience enhancement framework for an integrated electricity-gas-transportation coupled system oriented to energy internet. In this framework, a minimax regret robust optimization model considering the uncertainty of extreme disaster attacks is developed to make the line hardening strategy in the pre-disaster stage, which is solved by the column-and-constraint generation algorithm. Furthermore, the synthetic restoration model considering the co-optimization of dynamic dispatch of gas-fired units, network reconfiguration and damaged component repair is established, in which the coupling influence of the gas and transportation networks on the restoration strategy during the disaster and post disaster stages is taken into account. And the sequential cone programming method and generalized Benders decomposition algorithm is implemented to solve the above model. Finally, the proposed model and solution method are validated via a modified 33-bus power distribution network coupled with a 12-node transportation network and a 7-node gas network. The simulation results demonstrate that the proposed minmax regret robust optimization model can achieve a pre-disaster defensive strategy with less conservativeness in contrast to the conventional robust optimization model. Specifically, the cost under the worst-case attacks by the former has reduced by 11.52–22.29% compared to the latter. Moreover, the influence of the interdependent critical infrastructure networks on the synthetic restoration strategy in the disaster and post-disaster stages has been investigated. In particular, the power output by gas-fired units has reduced by 2699 kW when considering the operation constraints of the gas network. Additionally, due to the time-varying characteristics of traffic flow and commuting time in the transportation network, the repair time for the damaged components is shortened by 1.09 h while the preparation time of crews changes from 2.5 to 1.5 h.

Partial differential grey model based on control matrix and its application in short-term traffic flow prediction

Short-term traffic flow analysis is the core part of the intelligent transportation system, and also the critical basis for traffic management and control system to guide traffic flow. Real-time and accurate short-term traffic flow prediction can be effectively applied to traffic control and guidance, providing reliable and effective information for traffic managers and travelers, and improving travel efficiency. Based on the spatiotemporal characteristics of traffic flow and periodicity of traffic flow, this paper uses partial differential equation variables to reflect the spatiotemporal characteristics of traffic flow, combines the modelling mechanism of partial differential and the grey prediction model organically, and establishes a partial grey prediction model with control matrix by using the partial derivatives of the mean sequence. At the same time, the parameters estimation and modelling steps of the novel model are obtained by matrix analysis and recursion. A set of data is used from two perspectives to verify the proposed model's effectiveness. Experimental results show that the proposed model is stable and effective. Finally, the novel model is applied to the short-time traffic flow simulation and prediction of the highway. The research results show that the novel model is better than other comparison models. The novel model mainly aims at the matrix data form of traffic flow and is applied to general short-term traffic flow prediction. On the one hand, the prediction results of the novel model can provide theoretical basis and basic methods for the traffic management system, traffic data for traffic information system, and new ideas for the traffic flow prediction research. On the other hand, it can help traffic managers solve accurate real-time traffic flow information, provide real-time traffic information for travelers, and help them plan and adjust routes in advance.