Traffic Flux Research Articles

Towards Predictive Pollution Control Through Traffic Flux Forecasting With Deep Learning: A Case Study in the City of Valencia

ABSTRACTTraffic congestion represents a significant urban challenge, with notable implications for public health and environmental well‐being. Consequently, urban decision‐makers prioritize the mitigation of congestion. This study delves into the efficacy of harnessing extensive data on urban traffic dynamics, coupled with comprehensive knowledge of road networks, to enable Artificial Intelligence (AI) in forecasting traffic flux well in advance. Such forecasts hold promise for informing emission reduction measures, particularly those aligned with Low Emission Zone policies. The investigation centers on Valencia, leveraging its robust traffic sensor infrastructure, one of the most densely deployed worldwide, encompassing approximately 3500 sensors strategically positioned across the city. Employing historical data spanning 2016 and 2017, we undertake the task of training and characterizing a Long Short‐Term Memory (LSTM) Neural Network for the prediction of temporal traffic patterns. Our findings demonstrate the LSTM's efficacy in real‐time forecasting of traffic flow evolution, facilitated by its ability to discern salient patterns within the dataset.

Neural Network based Route Guidance Strategy in intelligent transportation systems

Traffic congestion in urban areas presents a significant challenge to efficient transportation and sustainable urban development. This paper introduces a Neural Network based Route Guidance Strategy to address the non-linear complexities of urban traffic flow. The strategy demonstrates its capability to optimize traffic flow in real-time by predicting the travel times of candidate routes. A comprehensive simulation study compares the performance of the Neural Network Strategy with traditional traffic management strategies, focusing on traffic flow efficiency, vehicle count stability, and route choice optimization. The results indicate that the Neural Network Strategy significantly enhances traffic management by stabilizing vehicle counts, reducing fluctuations in traffic flux, and achieving a more uniform distribution of vehicles. The paper concludes with an analysis of the experimental results, highlighting the integration of neural networks into traffic management systems as a promising approach to mitigating urban traffic congestion. Future research directions are discussed, emphasizing the potential for real-world implementation and the exploration of advanced neural network models.

Traffic jam mitigation by the policy of maximum velocity limitation

This study explored whether a policy with maximum velocity limitation prior to each jam point in a traffic flow system can mitigate jam situations in a highway. To quantify this question, a new cellular automata traffic model based on the Revised S-NFS model was established. We perused two specific scenarios: a jam naturally brought by a high traffic density, and one brought by a lane-closed section placed as an explicit bottleneck. The result of multi-agent simulation (MAS) reveals that such maximum velocity limitation policy can certainly mitigate jam situations when each jam is naturally bought up not by a bottleneck, as proved by several statistics, and cannot improve the traffic flux.

The optimal estimation of delayed flux effect on traffic stability in lattice hydrodynamic model

In the process of traffic information transmission, traffic flux delay often occurs. To solve traffic jams resulting from traffic flux delay, we put forward a novel feedback control mode to establish a lattice model accounting for the difference between the optimal estimation and the delayed flux (called for OEDF model). The stability condition, which is closely related to the OEDF model, is derived according to the linear stability analysis. Moreover, the important positive contribution of the OEDF model is demonstrated via numerical simulation from two aspects including density evolution and hysteresis loop, respectively.

Rail head surface defect magnetic flux leakage signal filtering based on the relativity among the adjacent sensors

Rail is the infrastructure of railway traffic and magnetic flux leakage (MFL) is commonly used to detect the surface defects of ferromagnetic materials such as rail. A correlation-based filtering method is proposed to inhibit the lift-off jamming in MFL detection for the defects in the rail head surface. The detection data is segmented and the two sensors with the minimum correlation coefficient of their outputs in the × direction are found. The possible defect width and depth according to the maximum of each output is estimated and the leakage magnetic field (LMF) of it is calculated. The output of the sensor with smaller correlation coefficient between the calculation LMF and the sensor output is chosen as the reference signal to filter. An experimental system was constructed to detect the artificial defects in the rail head surface, and the experimental results shown that the method reduces the lift-off jamming.

RMGen: A Tri-Layer Vehicular Trajectory Data Generation Model Exploring Urban Region Division and Mobility Pattern

As an important branch of the Internet of Things (IoT), the Internet of Vehicles (IoV) has attracted extensive attention in the research field. To deeply study the IoV and build a vehicle spatiotemporal interaction network, it is necessary to use the trajectory data of private cars. However, due to privacy and security protection policies and other reasons, the data set of private cars cannot be obtained, which hinders the research on the social attributes of vehicles in the IoV. Most of the previous work generated the same type of data, and how to generate private car data sets from various existing data sets is a huge challenge. In this paper, we propose a tri-layer framework to solve this problem. First, we propose a novel region division scheme that considers detailed inter-region relations connected by traffic flux. Second, a new spatial-temporal interaction model is developed to estimate the traffic flow between two regions. Third, we devise an evaluation pipeline to validate generation results from microscopic and macroscopic perspectives. Qualitative and quantitative results demonstrate that the data generated in heavy density scenarios can provide strong data support for downstream IoV and mobility research tasks.

Revealing spatiotemporal matching patterns between traffic flux and road resources using big geodata - A case study of Beijing

Mismatch between road system and spatiotemporal heterogeneity of traffic flow is a key reason for traffic congestion. Existing studies mainly focus on local regions or specific times (morning and evening peak), while the spatiotemporal heterogeneity of match and its causes, especially at larger scales, are still insufficiently studied. Herein, we proposed a framework for analyzing the match between traffic flux, i.e. the number of individuals driving into or out of a region per unit time, and road resources, using mobile phone data covering approximately 17 million users over one week in Beijing. Matches were measured through comparisons between the share of traffic flux and that of road resources both globally and locally. First, a global analysis with Gini coefficient revealed the match in Beijing is at a long-lasting low level. Then, the spatiotemporal disparity of match was examined via our proposed regional match index. Specifically, overallocated areas (traffic flux exceeds its corresponding shares of road resources) were mainly along arterial roads, while underallocated ones were in suburbs and gated residential communities. To explore the mechanism, four spatiotemporal matching modes were identified through a time series clustering method, and their distributions were explained by urban function based on ‘point-of-interest’ data.

On Solving a Class of Continuous Traffic Equilibrium Problems and Planning Facility Location Under Congestion

This paper presents methods to obtain analytical solutions to a class of continuous traffic equilibrium problems, where continuously distributed customers from a bounded two-dimensional service region seek service from one of several discretely located facilities via the least congested travel path. We show that under certain conditions, the traffic flux at equilibrium, which is governed by a set of partial differential equations, can be decomposed with respect to each facility and solved analytically. This finding paves the foundation for an efficient solution scheme. Closed-form solution to the equilibrium problem can be obtained readily when the service region has a certain regular shape, or through an additional conformal mapping if the service region has an arbitrary simply connected shape. These results shed light on some interesting properties of traffic equilibrium in a continuous space. This paper also discusses how service facility locations can be easily optimized by incorporating analytical formulas for the total generalized cost of spatially distributed customers under congestion. Examples of application contexts include gates or booths for pedestrian traffic, as well as launching sites for air vehicles. Numerical examples are used to show the superiority of the proposed optimization framework, in terms of both solution quality and computation time, as compared with traditional approaches based on discrete mathematical programming and partial differential equation solution methods. An example with the metro station entrances at the Beijing Railway Station is also presented to illustrate the usefulness of the proposed traffic equilibrium and location design models.

Effect of connected and autonomous vehicles on traffic flow at a bidirectional road

The objective of this study was to investigate the impact of connected and autonomous vehicles (CAVs) on traffic flow under various parameters. For this purpose, we propose a mixed CAV and conventional vehicle (CV) model to investigate a bidirectional two-lane traffic flow under the periodic boundary condition. The traffic flux and the phase diagrams of the system in the ([Formula: see text]) area are constructed in both cases: with and without CAVs. The overtaking frequency is also calculated. The simulation findings show that the traffic capacity is greatly enhanced with the increase in the CAV penetration ratio. Owing to the cooperative driving strategy, with the increase in penetration ratio of the CAV, the portion of smooth overtaking is boosted. Furthermore, it is found that the traffic throughput is positively correlated to the speed limit of the fast vehicle where the flux increases as [Formula: see text] increases. Also, even if there is a low rate of slow moving vehicles in the system, it will have an appreciable and a significant negative influence.

Infection transmission and prevention in metropolises with heterogeneous and dynamic populations

Due to dense social contacts, metropolises are considered as epicenters of contagious infectious diseases. Developing models for infection transmission and mitigation in metropolises is a challenging problem because of spatiotemporal variations in their population structures. Employing the fact that intra-urban mobility is mainly shaped by the transportation infrastructure and reflected in the traffic flux information, a novel multi-scale reaction-diffusion process is developed to model infection transmission in a metropolis.To mitigate the infection, the impact of three non-pharmaceutical preventive interventions (movement restrictions, social distancing, and proactive testing/screening) is analytically investigated on the reaction-diffusion process. We show that imposing movement restrictions between sub-urban areas is only beneficial when they have different reproduction numbers. The social distancing reduces the infection peak in sub-urban areas, but its impact on the entire metropolis is various: The social distancing reduces a metropolis's infection peak if its implementation disperses the reproduction number of sub-urban areas. We show that allocation schemes of proactive testing/screening teams to sub-urban areas have intractable impacts on the infection peak. This demonstrates the necessity of employing optimization techniques to design the best allocation scheme.Finally, three mathematical models and their solution approaches are developed to optimize the implementation of the interventions with the least economic burden. The performance of the optimization models is compared with two simpler implementation schemes (uniform and pro rata implementations of interventions) using the information of Sioux Falls metropolitan area in the U.S.

Monte Carlo Simulation in a Peruvian Highway

Highways and roads are important for nations' development and life quality. This is not different for Peru. A highway project called Daniel Alcides Carrión is expected to provide a solution to the over-employed Carretera Central road. This is a multimillionaire and important infrastructure project. Hence, it is important to evaluate the possible sustainability risks. In consequence, this study employed the Monte Carlo simulation for such a purpose. First, variables have been chosen and segregated into input and output. Variables like the initial investment, recurrent maintenance, periodical maintenance, savings in the operative cost of vehicles, and time savings employed the triangular distribution. Traffic growth and inflation rate employed the Pert distribution. The project's Net Present Value and Internal Rate of Return have been selected as output variables. Crystal Ball software has been employed to perform the Monte Carlo analysis. Consequently, this research found a high probability that the highway can become a profitable project due to its Net Present Value and Internal Rate of Return. Moreover, savings in operative costs of vehicles and traffic growth rate had positive impacts on the project's Net Present Value. However, the initial investment had a negative relationship with the output variable. Hence, the new highway should take prevision policies to maintain traffic flux. Thus, avoid closures that can have both human and natural sources. This study is the first in the Peruvian academic literature regarding highways risk analysis. Moreover, this study provides researchers, state officials, future highway managers, and users' valuable information to elaborate preventive measures to maintain the highway's social sustainability and increase its benefits.

Switching to electric vehicles can lead to significant reductions of PM2.5 and NO2 across China

Switching to electric vehicles can lead to significant reductions of PM2.5 and NO2 across China

Delay-independent traffic flux control for a discrete-time lattice hydrodynamic model with time-delay

A discrete-time lattice hydrodynamic model with time-delay and delay-independent traffic flux control signal is introduced. The new model is analyzed with the discrete-time Lyapunov stability theorem and a sufficient stable condition of the model is presented in the form of linear matrix inequality. Through numerical simulation, the traffic flow evolution rules under different conditions of time-delay and control gain are demonstrated and compared. All the results show that the traffic system with time-delay can easily evolve into traffic congestion comparing to the traffic system without time-delay. Also the discrete-time traffic flux control signal can improve the stable level of traffic flow.

COVID-19 Full Lockdowns Expose Significant Air Quality Benefits Towards Electric Vehicles in China

Electric vehicles (EVs) represent a major path for global decarbonization, improvement of air quality and promotion of renewable energy. To tackle the COVID-19 pandemic, China imposed full lockdowns and thorough travel restrictions. This event represents an unprecedented inadvertent geoengineering experiment in vehicle emissions, emulating transition to EVs. Here we novelly exploited observations of air quality during the full lockdown to constrain predictions of a comprehensive chemical transport model. Large traffic flux reductions were near-linearly linked to reductions of NO 2 and PM 2.5 (correlation = 0.491 ~ 0.626). Extrapolating to a full conversion to EV results in a large reduction of PM 2.5 (30 ~ 70%) in most of central and south eastern China. A smaller reduction of PM 2.5 (10 ~ 20%) in Beijing and Tianjin was achievable due to the presence of major industrial emission sources which cause haze at a regional scale. The potential reductions in NO 2 were 40 ~ 90% in most of the megacities. At this present crossroads of policy, our findings reveal timely evidence supporting the transition towards renewable energy.Funding: This study is supported by the Department of Science and Technology of China (No. 2016YFC0202702, 2018YFC0213506 and 2018YFC0213503), National Research Program for Key Issues in Air Pollution Control in China (No. DQGG0107) and National Natural Science Foundation of China (No. 21577126, 41561144004, 21625701). Pengfei Li is supported by Initiation Fund for Introducing Talents of Hebei Agricultural University (412201904) and Youth Top Fund of Universities in Hebei Province (BJ2020032). Conflict of Interest: Authors declare no competing interests.

Stability analysis for a new lattice hydrodynamic model with time-varying delay in sensing traffic flux

This paper proposed a new macro lattice hydrodynamic model by considering the time-varying delayed information of the preceding lattice’ traffic flux. The influence of time-varying delayed traffic flux on traffic flow is studied by Lyapunov stability theory and the stable condition is given in terms of linear matrix inequality. Also numerical simulations for traffic flow with time-varying delay or not are conducted to explicitly show the impact of time-varying delayed traffic flux on traffic stability. The results demonstrate that the time-varying delayed traffic flux can weaken the stability of traffic flow and the traffic flow is more likely to develop into congestion with time-varying delayed information.

An Analysis of A Three-Phase Versus A Four-Phase Traffic Lights Regulation for A Four-Leg Intersection

Traffic management of intersections is an important factor that can determine traffic density at the intersection, as well as its surrounding. Long traffic queues we encounter in daily life, were often caused by ineffectiveness of traffic lights management of the cross sections.In this article, an analytic study of traffic light management of a four-leg intersection, based on the kinematic LWR model, was presented. Comparison was based on observing the end of queues over three cycles of red-green lights, under the assumption of a constant traffic flux. On every leg of the intersection, the end of the queues were obtained from characteristic lines of the shock waves.From these observations, the three phase regulation was preferred over the four-phase one. Finally, a case study of Taman Sari - Baltos intersection located in Bandung City, Indonesia, was discussed. Parameter values used in these simulations were obtained from direct observation.

Automated vehicle control systems need to solve social dilemmas to be disseminated

Abstract A new cellular automata traffic model based on the revised S-NFS model was established to consider a mixed flow of automated and human-driven vehicles assuming a multi-lane system. The model further classified automated vehicles into two categories: (1) vehicles with adaptive cruise control and (2) those with cooperative adaptive cruise control that supports so-called platoon driving. A vehicle that favors maximizing individual payoff, which ensures minimizing its own travel time, while maximizing global traffic flux was expected as the entire society. Intensive simulations, wherein automated and human-driven vehicles were presumed as cooperative (C) and defective (D) strategies, respectively, revealed that a D-strategy is always better than a C-strategy to maximize individual payoff as long as a smaller cooperative fraction is imposed. Meanwhile, social optimal could be realized by a situation comprising only automated vehicles. Such a stag-hunt social dilemma implied that an automated vehicle control system (AVCS) cannot permeate into a population of human-driven vehicles if the dissemination stage starts from a single vehicle with an AVCS.

Lattice hydrodynamic modeling with continuous self-delayed traffic flux integral and vehicle overtaking effect

This paper presents a new lattice hydrodynamic model with vehicle overtaking and the continuous self-delayed traffic flux integral. The linear stability condition of the model is derived through the linear stability analysis, which shows that the stable region can be enlarged by increasing the step of delay time. The modified Korteweg–de Vries (mKdV) equation is formulated through nonlinear analysis to describe the propagating behavior of traffic density wave near the critical point. The kink–anti-kink solution under different passing constants is also obtained. Results show that when the passing constant is lower than a threshold (Case I) that is associated with the delay time step, uniform flow and kink jam phase exhibits, and jamming transition occurs between the uniform flow and kink jam. When the passing constant exceeds the threshold (Case II), jamming transitions occur from uniform traffic flow to kink-Bando traffic wave through chaotic phase with decreasing sensitivity. Simulation examples verify that when the delay time increases from 0 to 0.6, the fluctuation amplitude of the traffic density is reduced from 0.07 to 0 even with exogenous initial disturbance, whereas under Case II, chaotic traffic flow appears when the density ranges from 0.18 to 0.31 and the delay time is 0.6.

Output-Feedback PDE Control of Traffic Flow on Cascaded Freeway Segments

We develop in this paper a boundary output feedback control law for an underactuated network of traffic flow on two connected roads; one incoming and one outgoing road connected by a junction. The macroscopic traffic dynamics on each road segment are governed by Aw-Rascle-Zhang (ARZ) model, consisting of second-order nonlinear partial differential equations (PDEs) of traffic density and velocity. The control objective is to stabilize the traffic network system on both roads around a chosen reference system. Using a ramp metering located at the outlet of the outgoing road, we actuate the traffic flux leaving this considered domain. Boundary measurements of traffic flux and velocity are taken at the junction connecting the two road segments. A delay-robust full state feedback control law and a boundary observer are designed for this under-actuated network of two systems interconnected through their boundaries. Each system consists of two hetero-directional linear first-order hyperbolic PDEs. The exponential convergence to the reference system is achieved.

Stationary solution of semi-discrete traffic flow model on a ring road with slopes

The traffic bottleneck effects are investigated on a ring road with up- and down-slopes to the semi-discrete model under the Lagrange coordinate. The kinetic wave theory is applied to discuss all types of stationary solutions for a small relaxation time. Moreover, the analytical formulas of the queuing lengths before bottlenecks and the critical densities of the saturated flux are derived. The stability of the stationary solution on every road section under different mass increments is discussed. The relation between the slope gradient and saturated flux platform is also obtained. The numerical simulation reproduces many complex nonlinear phenomena, such as the steady-state flow, oscillatory congested traffic and saturated flux platform. This study helps to explain the empirical features on inhomogeneous roads in the real-world traffic.