Accurate short-term traffic flow prediction plays a crucial role in intelligent transportation system (ITS), because it can assist both traffic authorities and individual travelers make better decisions. Previous rese...Accurate short-term traffic flow prediction plays a crucial role in intelligent transportation system (ITS), because it can assist both traffic authorities and individual travelers make better decisions. Previous researches mostly focus on shallow traffic prediction models, which performances were unsatisfying since short-term traffic flow exhibits the characteristics of high nonlinearity, complexity and chaos. Taking the spatial and temporal correlations into consideration, a new traffic flow prediction method is proposed with the basis on the road network topology and gated recurrent unit (GRU). This method can help researchers without professional traffic knowledge extracting generic traffic flow features effectively and efficiently. Experiments are conducted by using real traffic flow data collected from the Caltrans Performance Measurement System (PEMS) database in San Diego and Oakland from June 15, 2017 to September 27, 2017. The results demonstrate that our method outperforms other traditional approaches in terms of mean absolute percentage error (MAPE), symmetric mean absolute percentage error (SMAPE) and root mean square error (RMSE).展开更多
Accurate forecasting of traffic flow provides a powerful traffic decision-making basis for an intelligent transportation system. However, the traffic data's complexity and fluctuation, as well as the noise produce...Accurate forecasting of traffic flow provides a powerful traffic decision-making basis for an intelligent transportation system. However, the traffic data's complexity and fluctuation, as well as the noise produced during collecting information and summarizing original data of traffic flow, cause large errors in the traffic flow forecasting results. This article suggests a solution to the above mentioned issues and proposes a fully connected time-gated neural network based on wavelet reconstruction(WT-FCTGN). To eliminate the potential noise and strengthen the potential traffic trend in the data, we adopt the methods of wavelet reconstruction and periodic data introduction to preprocess the data. The model introduces fully connected time-series blocks to model all the information including time sequence information and fluctuation information in the flow of traffic, and establishes the time gate block to comprehend the periodic characteristics of the flow of traffic and predict its flow. The performance of the WT-FCTGN model is validated on the public Pe MS data set. The experimental results show that the WT-FCTGN model has higher accuracy, and its mean absolute error(MAE), mean absolute percentage error(MAPE) and root mean square error(RMSE) are obviously lower than those of the other algorithms. The robust experimental results prove that the WT-FCTGN model has good anti-noise ability.展开更多
With the development of intelligent and interconnected traffic system,a convergence of traffic stream is anticipated in the foreseeable future,where both connected automated vehicle(CAV)and human driven vehicle(HDV)wi...With the development of intelligent and interconnected traffic system,a convergence of traffic stream is anticipated in the foreseeable future,where both connected automated vehicle(CAV)and human driven vehicle(HDV)will coexist.In order to examine the effect of CAV on the overall stability and energy consumption of such a heterogeneous traffic system,we first take into account the interrelated perception of distance and speed by CAV to establish a macroscopic dynamic model through utilizing the full velocity difference(FVD)model.Subsequently,adopting the linear stability theory,we propose the linear stability condition for the model through using the small perturbation method,and the validity of the heterogeneous model is verified by comparing with the FVD model.Through nonlinear theoretical analysis,we further derive the KdV-Burgers equation,which captures the propagation characteristics of traffic density waves.Finally,by numerical simulation experiments through utilizing a macroscopic model of heterogeneous traffic flow,the effect of CAV permeability on the stability of density wave in heterogeneous traffic flow and the energy consumption of the traffic system is investigated.Subsequent analysis reveals emergent traffic phenomena.The experimental findings demonstrate that as CAV permeability increases,the ability to dampen the propagation of fluctuations in heterogeneous traffic flow gradually intensifies when giving system perturbation,leading to enhanced stability of the traffic system.Furthermore,higher initial traffic density renders the traffic system more susceptible to congestion,resulting in local clustering effect and stop-and-go traffic phenomenon.Remarkably,the total energy consumption of the heterogeneous traffic system exhibits a gradual decline with CAV permeability increasing.Further evidence has demonstrated the positive influence of CAV on heterogeneous traffic flow.This research contributes to providing theoretical guidance for future CAV applications,aiming to enhance urban road traffic efficiency and alleviate congestion.展开更多
Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel efficiency.To improve prediction accuracy,a crucial...Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel efficiency.To improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic data.In recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic data.However,most models ignore the semantic spatial similarity between long-distance areas when mining spatial dependency.They also ignore the impact of predicted time steps on the next unpredicted time step for making long-term predictions.Moreover,these models lack a comprehensive data embedding process to represent complex spatiotemporal dependency.This paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in cities.MSPSTT adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these issues.The model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic characteristics.The spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term prediction.Experiments on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.展开更多
This paper introduces an innovative approach to the synchronized demand-capacity balance with special focus on sector capacity uncertainty within a centrally controlled collaborative air traffic flow management(ATFM)f...This paper introduces an innovative approach to the synchronized demand-capacity balance with special focus on sector capacity uncertainty within a centrally controlled collaborative air traffic flow management(ATFM)framework.Further with previous study,the uncertainty in capacity is considered as a non-negligible issue regarding multiple reasons,like the impact of weather,the strike of air traffic controllers(ATCOs),the military use of airspace and the spatiotemporal distribution of nonscheduled flights,etc.These recessive factors affect the outcome of traffic flow optimization.In this research,the focus is placed on the impact of sector capacity uncertainty on demand and capacity balancing(DCB)optimization and ATFM,and multiple options,such as delay assignment and rerouting,are intended for regulating the traffic flow.A scenario optimization method for sector capacity in the presence of uncertainties is used to find the approximately optimal solution.The results show that the proposed approach can achieve better demand and capacity balancing and determine perfect integer solutions to ATFM problems,solving large-scale instances(24 h on seven capacity scenarios,with 6255 flights and 8949 trajectories)in 5-15 min.To the best of our knowledge,our experiment is the first to tackle large-scale instances of stochastic ATFM problems within the collaborative ATFM framework.展开更多
An improved multiple car-following model is proposed by considering the arbitrary number of preceding cars, which includes both the headway and the velocity difference of multiple preceding cars. The stability conditi...An improved multiple car-following model is proposed by considering the arbitrary number of preceding cars, which includes both the headway and the velocity difference of multiple preceding cars. The stability condition of the extended model is obtained by using the linear stability theory. The modified Korteweg-de Vries equation is derived to describe the traffic behaviour near the critical point by applying the nonlinear analysis. Traffic flow can be also divided into three regions： stable metastable and unstable regions. Numerical simulation is in accordance with the analytical result for the model. And numerical simulation shows that the stabilisation of traffic is increasing by considering the information of more leading cars and there is unavoidable effect on traffic flow from the multiple leading cars information.展开更多
In this paper, we incorporate new parameters into a cellular automaton traffic flow model proposed in our previous paper [Jin et al. 2010 J. Stat. Mech. 2010 P03018]. Through these parameters, we adjust the anticipate...In this paper, we incorporate new parameters into a cellular automaton traffic flow model proposed in our previous paper [Jin et al. 2010 J. Stat. Mech. 2010 P03018]. Through these parameters, we adjust the anticipated velocity and the acceleration threshold separately. It turns out that the flow rate of synchronized flow mainly changes with the anticipated velocity, and the F →S phase transition feature mainly changes with the acceleration threshold. Therefore, we conclude that the acceleration threshold is the major factor affecting the F → S phase transition.展开更多
In this paper, a recently introduced cellular automata （CA） model is used for a statistical analysis of the inner micro-scopic structure of synchronized traffic flow. The analysis focuses on the formation and dissol...In this paper, a recently introduced cellular automata （CA） model is used for a statistical analysis of the inner micro-scopic structure of synchronized traffic flow. The analysis focuses on the formation and dissolution of clusters or platoons of vehicles, as the mechanism that causes the presence of this synchronized traffic state with a high flow. This platoon formation is one of the most interesting phenomena observed in traffic flows and plays an important role both in manual and automated highway systems （AHS）. Simulation results, obtained from a single-lane system under periodic boundary conditions indicate that in the density region where the synchronized state is observed, most vehicles travel together in pla- toons with approximately the same speed and small spatial distances. The examination of velocity variations and individual vehicle gaps shows that the flow corresponding to the synchronized state is stable, safe and highly correlated. Moreover, results indicate that the observed platoon formation in real traffic is reproduced in simulations by the relation between vehicle headway and velocity that is embedded in the dynamics definition of the CA model.展开更多
On the basis of the full velocity difference （FVD） model, an improved multiple car-following （MCF） model is proposed by taking into account multiple information inputs from preceding vehicles. The linear stability...On the basis of the full velocity difference （FVD） model, an improved multiple car-following （MCF） model is proposed by taking into account multiple information inputs from preceding vehicles. The linear stability condition of the model is obtained by using the linear stability theory. Through nonlinear analysis, a modified Korteweg-de Vries equation is constructed and solved. The traffic jam can thus be described by the klnk-antikink soliton solution for the mKdV equation. The improvement of this new model over the previous ones lies in the fact that it not only theoretically retains many strong points of the previous ones, but also performs more realistically than others in the dynamical evolution of congestion. Furthermore, numerical simulation of traffic dynamics shows that the proposed model can avoid the disadvantage of negative velocity that occurs at small sensitivity coefficients λ in the FVD model by adjusting the information on the multiple leading vehicles. No collision occurs and no unrealistic deceleration appears in the improved model.展开更多
In this note, we consider the interactions of elementary waves for the traffic flow model proposed by Aw and Rascle when the vacuum is not involved. The solutions are obtained constructively and globally when the init...In this note, we consider the interactions of elementary waves for the traffic flow model proposed by Aw and Rascle when the vacuum is not involved. The solutions are obtained constructively and globally when the initial data consist of three pieces of constant states. Furthermore, it can be found that the Riemann solutions are stable with respect to such small perturbations of the initial data in this particular situation by investigating the limits of the solutions as the perturbed parameter ε goes to zero.展开更多
Accurate prediction of road traffic flow is a significant part in the intelligent transportation systems.Accurate prediction can alleviate traffic congestion,and reduce environmental pollution.For the management depar...Accurate prediction of road traffic flow is a significant part in the intelligent transportation systems.Accurate prediction can alleviate traffic congestion,and reduce environmental pollution.For the management department,it can make effective use of road resources.For individuals,it can help people plan their own travel paths,avoid congestion,and save time.Owing to complex factors on the road,such as damage to the detector and disturbances from environment,the measured traffic volume can contain noise.Reducing the influence of noise on traffic flow prediction is a piece of very important work.Therefore,in this paper we propose a combination algorithm of denoising and BILSTM to effectively improve the performance of traffic flow prediction.At the same time,three denoising algorithms are compared to find the best combination mode.In this paper,the wavelet(WL) denoising scheme,the empirical mode decomposition(EMD) denoising scheme,and the ensemble empirical mode decomposition(EEMD) denoising scheme are all introduced to suppress outliers in traffic flow data.In addition,we combine the denoising schemes with bidirectional long short-term memory(BILSTM)network to predict the traffic flow.The data in this paper are cited from performance measurement system(PeMS).We choose three kinds of road data(mainline,off ramp,on ramp) to predict traffic flow.The results for mainline show that data denoising can improve prediction accuracy.Moreover,prediction accuracy of BILSTM+EEMD scheme is the highest in the three methods(BILSTM+WL,BILSTM+EMD,BILSTM+EEMD).The results for off ramp and on ramp show the same performance as the results for mainline.It is indicated that this model is suitable for different road sections and long-term prediction.展开更多
Research on the stochastic behavior of traffic flow is important to understand the intrinsic evolution rules of a traffic system. By introducing an interactional potential of vehicles into the randomization step, an i...Research on the stochastic behavior of traffic flow is important to understand the intrinsic evolution rules of a traffic system. By introducing an interactional potential of vehicles into the randomization step, an improved cellular automata traffic flow model with variable probability of randomization is proposed in this paper. In the proposed model, the driver is affected by the interactional potential of vehicles before him, and his decision-making process is related to the interactional potential. Compared with the traditional cellular automata model, the modeling is more suitable for the driver＇s random decision-making process based on the vehicle and traffic situations in front of him in actual traffic. From the improved model, the fundamental diagram （flow^tensity relationship） is obtained, and the detailed high-density traffic phenomenon is reproduced through numerical simulation.展开更多
Based on the massive data collected with a passive network monitoring equipment placed in China＇s backbone, we present a deep insight into the network backbone traffic and evaluate various ways for inproving traffic ...Based on the massive data collected with a passive network monitoring equipment placed in China＇s backbone, we present a deep insight into the network backbone traffic and evaluate various ways for inproving traffic classifying efficiency in this pa- per. In particular, the study has scrutinized the net- work traffic in terms of protocol types and signatures, flow length, and port distffoution, from which mean- ingful and interesting insights on the current Intemet of China from the perspective of both the packet and flow levels are derived. We show that the classifica- tion efficiency can be greatly irrproved by using the information of preferred ports of the network applica- tions. Quantitatively, we find two traffic duration thresholds, with which 40% of TCP flows and 70% of UDP flows can be excluded from classification pro- cessing while the in^act on classification accuracy is trivial, i.e., the classification accuracy can still reach a high level by saving 85% of the resources.展开更多
This paper proposes a new traffic model to describe traffic flow with slope under consideration of the gravity effect.Based on the model,stability analysis is conducted and a numerical simulation is performed to explo...This paper proposes a new traffic model to describe traffic flow with slope under consideration of the gravity effect.Based on the model,stability analysis is conducted and a numerical simulation is performed to explore the characteristics of the traffic flow with slope.The result shows that the perturbation of the system is an inherent one,which is induced by the slope.In addition,the hysteresis loop is represented through plotting the figure of velocity against headway and highly depends on the slope angle. The kinematic wave at high density is also obtained through reproducing the phenomenon of stop-and-go traffic,which is significant to explore the phase transition of traffic flow and the evolution of traffic congestion.展开更多
Considering the effects that the probability of traffic interruption and the friction between two lanes have on the car-following behaviour, this paper establishes a new two-lane microscopic car-following model. Based...Considering the effects that the probability of traffic interruption and the friction between two lanes have on the car-following behaviour, this paper establishes a new two-lane microscopic car-following model. Based on this microscopic model, a new macroscopic model was deduced by the relevance relation of microscopic and macroscopic scale parameters for the two-lane traffic flow. Terms related to lane change are added into the continuity equations and velocity dynamic equations to investigate the lane change rate. Numerical results verify that the proposed model can be efficiently used to reflect the effect of the probability of traffic interruption on the shock, rarefaction wave and lane change behaviour on two-lane freeways. The model has also been applied in reproducing some complex traffic phenomena caused by traffic accident interruption.展开更多
This paper investigates the behaviour of traffic flow in traffic systems with a new model based on the NaSch model and cluster approximation of mean-field theory. The proposed model aims at constructing a mapping rela...This paper investigates the behaviour of traffic flow in traffic systems with a new model based on the NaSch model and cluster approximation of mean-field theory. The proposed model aims at constructing a mapping relationship between the microcosmic behaviour and the macroscopic property of traffic flow. Results demonstrate that scale-free phenomenon of the evolution network becomes obvious when the density value of traffic flow reaches at the critical point of phase transition from free flow to traffic congestion, and jamming is limited in this scale-free structure.展开更多
Internet of Car, resulting from the Internet of Things, is a key point for the forthcoming smart city. In this article, GPS technology, 3G wireless technology and cloud-processing technology are employed to construct ...Internet of Car, resulting from the Internet of Things, is a key point for the forthcoming smart city. In this article, GPS technology, 3G wireless technology and cloud-processing technology are employed to construct a cloud-processing network platform based on the Internet of Car. By this platform, positions and velocity of the running cars, information of traffic flow from fixed monitoring points and transportation videos are combined to be a virtual traffic flow data platform, which is a parallel system with real traffic flow and is able to supply basic data for analysis and decision of intelligent transportation system.展开更多
By introducing the traffic anticipation effect in the real world into the original lattice hydrodynamic model, we present a new anticipation effect lattice hydrodynamic （AELH） model, and obtain the linear stability ...By introducing the traffic anticipation effect in the real world into the original lattice hydrodynamic model, we present a new anticipation effect lattice hydrodynamic （AELH） model, and obtain the linear stability condition of the model by applying the linear stability theory. Through nonlinear analysis, we derive the Burgers equation and Korteweg-de Vries （KdV） equation, to describe the propagating behaviour of traffic density waves in the stable and the metastable regions, respectively. The good agreement between simulation results and analytical results shows that the stability of traffic flow can be enhanced when the anticipation effect is considered.展开更多
In light of previous work [Phys. Rev. E 60 4000 （1999）], a modified coupled-map car-following model is proposed by considering the headways of two successive vehicles in front of a considered vehicle described by th...In light of previous work [Phys. Rev. E 60 4000 （1999）], a modified coupled-map car-following model is proposed by considering the headways of two successive vehicles in front of a considered vehicle described by the optimal velocity function. The non-jam conditions are given on the basis of control theory. Through simulation, we find that our model can exhibit a better effect as p = 0.65, which is a parameter in the optimal velocity function. The control scheme, which was proposed by Zhao and Gao, is introduced into the modified model and the feedback gain range is determined. In addition, a modified control method is applied to a mixed traffic system that consists of two types of vehicle. The range of gains is also obtained by theoretical analysis. Comparisons between our method and that of Zhao and Gao are carried out, and the corresponding numerical simulation results demonstrate that the temporal behavior of traffic flow obtained using our method is better than that proposed by Zhao and Gao in mixed traffic systems.展开更多
In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is proposed.On the basis of previous studies,this paper expands the set o...In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is proposed.On the basis of previous studies,this paper expands the set of weather characteristics affecting the traffic flow in the terminal area,including weather forecast data and Meteorological Report of Aerodrome Conditions(METAR)data.The terminal airspace is divided into smaller areas based on function and the weather severity index(WSI)characteristics extracted from weather forecast data are established to better quantify the impact of weather.MICL model preserves the advantages of the convolution neural network(CNN)and the long short-term memory(LSTM)model,and adopts two channels to input WSI and METAR information,respectively,which can fully reflect the temporal and spatial distribution characteristics of weather in the terminal area.Multi-scene experiments are designed based on the real historical data of Guangzhou Terminal Area operating in typical convective weather.The results show that the MICL model has excellent performance in mean squared error(MSE),root MSE(RMSE),mean absolute error(MAE)and other performance indicators compared with the existing machine learning models or deep learning models,such as Knearest neighbor(KNN),support vector regression(SVR),CNN and LSTM.In the forecast period ranging from 30 min to 6 h,the MICL model has the best prediction accuracy and stability.展开更多
基金Supported by the Support Program of the National 12th Five Year-Plan of China(2015BAK25B03)
文摘Accurate short-term traffic flow prediction plays a crucial role in intelligent transportation system (ITS), because it can assist both traffic authorities and individual travelers make better decisions. Previous researches mostly focus on shallow traffic prediction models, which performances were unsatisfying since short-term traffic flow exhibits the characteristics of high nonlinearity, complexity and chaos. Taking the spatial and temporal correlations into consideration, a new traffic flow prediction method is proposed with the basis on the road network topology and gated recurrent unit (GRU). This method can help researchers without professional traffic knowledge extracting generic traffic flow features effectively and efficiently. Experiments are conducted by using real traffic flow data collected from the Caltrans Performance Measurement System (PEMS) database in San Diego and Oakland from June 15, 2017 to September 27, 2017. The results demonstrate that our method outperforms other traditional approaches in terms of mean absolute percentage error (MAPE), symmetric mean absolute percentage error (SMAPE) and root mean square error (RMSE).
基金The Science and Technology Research and Development Program Project of China Railway Group Ltd provided funding for this study(Project Nos.2020-Special-02 and 2021Special-08)。
文摘Accurate forecasting of traffic flow provides a powerful traffic decision-making basis for an intelligent transportation system. However, the traffic data's complexity and fluctuation, as well as the noise produced during collecting information and summarizing original data of traffic flow, cause large errors in the traffic flow forecasting results. This article suggests a solution to the above mentioned issues and proposes a fully connected time-gated neural network based on wavelet reconstruction(WT-FCTGN). To eliminate the potential noise and strengthen the potential traffic trend in the data, we adopt the methods of wavelet reconstruction and periodic data introduction to preprocess the data. The model introduces fully connected time-series blocks to model all the information including time sequence information and fluctuation information in the flow of traffic, and establishes the time gate block to comprehend the periodic characteristics of the flow of traffic and predict its flow. The performance of the WT-FCTGN model is validated on the public Pe MS data set. The experimental results show that the WT-FCTGN model has higher accuracy, and its mean absolute error(MAE), mean absolute percentage error(MAPE) and root mean square error(RMSE) are obviously lower than those of the other algorithms. The robust experimental results prove that the WT-FCTGN model has good anti-noise ability.
基金Project supported by the Fundamental Research Funds for Central Universities,China(Grant No.2022YJS065)the National Natural Science Foundation of China(Grant Nos.72288101 and 72371019).
文摘With the development of intelligent and interconnected traffic system,a convergence of traffic stream is anticipated in the foreseeable future,where both connected automated vehicle(CAV)and human driven vehicle(HDV)will coexist.In order to examine the effect of CAV on the overall stability and energy consumption of such a heterogeneous traffic system,we first take into account the interrelated perception of distance and speed by CAV to establish a macroscopic dynamic model through utilizing the full velocity difference(FVD)model.Subsequently,adopting the linear stability theory,we propose the linear stability condition for the model through using the small perturbation method,and the validity of the heterogeneous model is verified by comparing with the FVD model.Through nonlinear theoretical analysis,we further derive the KdV-Burgers equation,which captures the propagation characteristics of traffic density waves.Finally,by numerical simulation experiments through utilizing a macroscopic model of heterogeneous traffic flow,the effect of CAV permeability on the stability of density wave in heterogeneous traffic flow and the energy consumption of the traffic system is investigated.Subsequent analysis reveals emergent traffic phenomena.The experimental findings demonstrate that as CAV permeability increases,the ability to dampen the propagation of fluctuations in heterogeneous traffic flow gradually intensifies when giving system perturbation,leading to enhanced stability of the traffic system.Furthermore,higher initial traffic density renders the traffic system more susceptible to congestion,resulting in local clustering effect and stop-and-go traffic phenomenon.Remarkably,the total energy consumption of the heterogeneous traffic system exhibits a gradual decline with CAV permeability increasing.Further evidence has demonstrated the positive influence of CAV on heterogeneous traffic flow.This research contributes to providing theoretical guidance for future CAV applications,aiming to enhance urban road traffic efficiency and alleviate congestion.
基金the National Natural Science Foundation of China under Grant No.62272087Science and Technology Planning Project of Sichuan Province under Grant No.2023YFG0161.
文摘Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel efficiency.To improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic data.In recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic data.However,most models ignore the semantic spatial similarity between long-distance areas when mining spatial dependency.They also ignore the impact of predicted time steps on the next unpredicted time step for making long-term predictions.Moreover,these models lack a comprehensive data embedding process to represent complex spatiotemporal dependency.This paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in cities.MSPSTT adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these issues.The model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic characteristics.The spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term prediction.Experiments on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.
文摘This paper introduces an innovative approach to the synchronized demand-capacity balance with special focus on sector capacity uncertainty within a centrally controlled collaborative air traffic flow management(ATFM)framework.Further with previous study,the uncertainty in capacity is considered as a non-negligible issue regarding multiple reasons,like the impact of weather,the strike of air traffic controllers(ATCOs),the military use of airspace and the spatiotemporal distribution of nonscheduled flights,etc.These recessive factors affect the outcome of traffic flow optimization.In this research,the focus is placed on the impact of sector capacity uncertainty on demand and capacity balancing(DCB)optimization and ATFM,and multiple options,such as delay assignment and rerouting,are intended for regulating the traffic flow.A scenario optimization method for sector capacity in the presence of uncertainties is used to find the approximately optimal solution.The results show that the proposed approach can achieve better demand and capacity balancing and determine perfect integer solutions to ATFM problems,solving large-scale instances(24 h on seven capacity scenarios,with 6255 flights and 8949 trajectories)in 5-15 min.To the best of our knowledge,our experiment is the first to tackle large-scale instances of stochastic ATFM problems within the collaborative ATFM framework.
基金Project supported by the Natural Science Foundation of Hunan Province,China (Grant No. 07JJ6106)the Important Project of Scientific Research Foundation of Hunan University of Arts and Science,China (Grant No. JJZD0902)the Fund of the 11th Five-year Plan for Key Construction Academic Subject of Hunan Province,China (Grant No. 06GXCD02)
文摘An improved multiple car-following model is proposed by considering the arbitrary number of preceding cars, which includes both the headway and the velocity difference of multiple preceding cars. The stability condition of the extended model is obtained by using the linear stability theory. The modified Korteweg-de Vries equation is derived to describe the traffic behaviour near the critical point by applying the nonlinear analysis. Traffic flow can be also divided into three regions： stable metastable and unstable regions. Numerical simulation is in accordance with the analytical result for the model. And numerical simulation shows that the stabilisation of traffic is increasing by considering the information of more leading cars and there is unavoidable effect on traffic flow from the multiple leading cars information.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 10872194 and 50738001)
文摘In this paper, we incorporate new parameters into a cellular automaton traffic flow model proposed in our previous paper [Jin et al. 2010 J. Stat. Mech. 2010 P03018]. Through these parameters, we adjust the anticipated velocity and the acceleration threshold separately. It turns out that the flow rate of synchronized flow mainly changes with the anticipated velocity, and the F →S phase transition feature mainly changes with the acceleration threshold. Therefore, we conclude that the acceleration threshold is the major factor affecting the F → S phase transition.
基金Project supported by the DGAPA,UNAM(Grant No.IN104913)
文摘In this paper, a recently introduced cellular automata （CA） model is used for a statistical analysis of the inner micro-scopic structure of synchronized traffic flow. The analysis focuses on the formation and dissolution of clusters or platoons of vehicles, as the mechanism that causes the presence of this synchronized traffic state with a high flow. This platoon formation is one of the most interesting phenomena observed in traffic flows and plays an important role both in manual and automated highway systems （AHS）. Simulation results, obtained from a single-lane system under periodic boundary conditions indicate that in the density region where the synchronized state is observed, most vehicles travel together in pla- toons with approximately the same speed and small spatial distances. The examination of velocity variations and individual vehicle gaps shows that the flow corresponding to the synchronized state is stable, safe and highly correlated. Moreover, results indicate that the observed platoon formation in real traffic is reproduced in simulations by the relation between vehicle headway and velocity that is embedded in the dynamics definition of the CA model.
基金Project supported by the National High Tech Research and Development Program of China (Grant No 511-0910-1031)the National "10th Five-year" Science and Technique Important Program of China (Grant No 2002BA404A07)
文摘On the basis of the full velocity difference （FVD） model, an improved multiple car-following （MCF） model is proposed by taking into account multiple information inputs from preceding vehicles. The linear stability condition of the model is obtained by using the linear stability theory. Through nonlinear analysis, a modified Korteweg-de Vries equation is constructed and solved. The traffic jam can thus be described by the klnk-antikink soliton solution for the mKdV equation. The improvement of this new model over the previous ones lies in the fact that it not only theoretically retains many strong points of the previous ones, but also performs more realistically than others in the dynamical evolution of congestion. Furthermore, numerical simulation of traffic dynamics shows that the proposed model can avoid the disadvantage of negative velocity that occurs at small sensitivity coefficients λ in the FVD model by adjusting the information on the multiple leading vehicles. No collision occurs and no unrealistic deceleration appears in the improved model.
基金Sponsored by National Natural Science Foundation of China (10901077)China Postdoctoral Science Foundation (201003504+1 种基金 20090451089)Shandong Provincial Doctoral Foundation (BS2010SF006)
文摘In this note, we consider the interactions of elementary waves for the traffic flow model proposed by Aw and Rascle when the vacuum is not involved. The solutions are obtained constructively and globally when the initial data consist of three pieces of constant states. Furthermore, it can be found that the Riemann solutions are stable with respect to such small perturbations of the initial data in this particular situation by investigating the limits of the solutions as the perturbed parameter ε goes to zero.
基金Project supported by the Program of Humanities and Social Science of the Education Ministry of China(Grant No.20YJA630008)the Natural Science Foundation of Zhejiang Province,China(Grant No.LY20G010004)the K C Wong Magna Fund in Ningbo University,China。
文摘Accurate prediction of road traffic flow is a significant part in the intelligent transportation systems.Accurate prediction can alleviate traffic congestion,and reduce environmental pollution.For the management department,it can make effective use of road resources.For individuals,it can help people plan their own travel paths,avoid congestion,and save time.Owing to complex factors on the road,such as damage to the detector and disturbances from environment,the measured traffic volume can contain noise.Reducing the influence of noise on traffic flow prediction is a piece of very important work.Therefore,in this paper we propose a combination algorithm of denoising and BILSTM to effectively improve the performance of traffic flow prediction.At the same time,three denoising algorithms are compared to find the best combination mode.In this paper,the wavelet(WL) denoising scheme,the empirical mode decomposition(EMD) denoising scheme,and the ensemble empirical mode decomposition(EEMD) denoising scheme are all introduced to suppress outliers in traffic flow data.In addition,we combine the denoising schemes with bidirectional long short-term memory(BILSTM)network to predict the traffic flow.The data in this paper are cited from performance measurement system(PeMS).We choose three kinds of road data(mainline,off ramp,on ramp) to predict traffic flow.The results for mainline show that data denoising can improve prediction accuracy.Moreover,prediction accuracy of BILSTM+EEMD scheme is the highest in the three methods(BILSTM+WL,BILSTM+EMD,BILSTM+EEMD).The results for off ramp and on ramp show the same performance as the results for mainline.It is indicated that this model is suitable for different road sections and long-term prediction.
基金supported by the National Natural Science Foundation of China(Grant Nos.11172247,61273021,61373009,and 61100118)
文摘Research on the stochastic behavior of traffic flow is important to understand the intrinsic evolution rules of a traffic system. By introducing an interactional potential of vehicles into the randomization step, an improved cellular automata traffic flow model with variable probability of randomization is proposed in this paper. In the proposed model, the driver is affected by the interactional potential of vehicles before him, and his decision-making process is related to the interactional potential. Compared with the traditional cellular automata model, the modeling is more suitable for the driver＇s random decision-making process based on the vehicle and traffic situations in front of him in actual traffic. From the improved model, the fundamental diagram （flow^tensity relationship） is obtained, and the detailed high-density traffic phenomenon is reproduced through numerical simulation.
基金This paper was partially supported by the National Natural Science Foundation of China under Crant No. 61072061111 Project of China under Crant No. B08004 the Fundamental Research Funds for the Central Universities under Grant No. 2009RC0122. References
文摘Based on the massive data collected with a passive network monitoring equipment placed in China＇s backbone, we present a deep insight into the network backbone traffic and evaluate various ways for inproving traffic classifying efficiency in this pa- per. In particular, the study has scrutinized the net- work traffic in terms of protocol types and signatures, flow length, and port distffoution, from which mean- ingful and interesting insights on the current Intemet of China from the perspective of both the packet and flow levels are derived. We show that the classifica- tion efficiency can be greatly irrproved by using the information of preferred ports of the network applica- tions. Quantitatively, we find two traffic duration thresholds, with which 40% of TCP flows and 70% of UDP flows can be excluded from classification pro- cessing while the in^act on classification accuracy is trivial, i.e., the classification accuracy can still reach a high level by saving 85% of the resources.
基金Project supported partially by the Strategic Research Grants from City University of Hong Kong (Grant Nos SRG 7002226(BC)and SRG 7002370(BC))the National Natural Science Foundation of China (Grant Nos 10662002,10672098 and 10532020)
文摘This paper proposes a new traffic model to describe traffic flow with slope under consideration of the gravity effect.Based on the model,stability analysis is conducted and a numerical simulation is performed to explore the characteristics of the traffic flow with slope.The result shows that the perturbation of the system is an inherent one,which is induced by the slope.In addition,the hysteresis loop is represented through plotting the figure of velocity against headway and highly depends on the slope angle. The kinematic wave at high density is also obtained through reproducing the phenomenon of stop-and-go traffic,which is significant to explore the phase transition of traffic flow and the evolution of traffic congestion.
基金Project supported by the National High Tech Research and Development Program of China (Grant No. 511-0910-1031)
文摘Considering the effects that the probability of traffic interruption and the friction between two lanes have on the car-following behaviour, this paper establishes a new two-lane microscopic car-following model. Based on this microscopic model, a new macroscopic model was deduced by the relevance relation of microscopic and macroscopic scale parameters for the two-lane traffic flow. Terms related to lane change are added into the continuity equations and velocity dynamic equations to investigate the lane change rate. Numerical results verify that the proposed model can be efficiently used to reflect the effect of the probability of traffic interruption on the shock, rarefaction wave and lane change behaviour on two-lane freeways. The model has also been applied in reproducing some complex traffic phenomena caused by traffic accident interruption.
基金supported by the National Basic Research Program of China (973) (Grant No 2006CB705500)the National Natural Science Foundation of China (Grant No 70671008)
文摘This paper investigates the behaviour of traffic flow in traffic systems with a new model based on the NaSch model and cluster approximation of mean-field theory. The proposed model aims at constructing a mapping relationship between the microcosmic behaviour and the macroscopic property of traffic flow. Results demonstrate that scale-free phenomenon of the evolution network becomes obvious when the density value of traffic flow reaches at the critical point of phase transition from free flow to traffic congestion, and jamming is limited in this scale-free structure.
基金supported by National Basic Research Program of China (973 Program) 2012CB821200 (2012CB821206)National Natural Science Foundation under Grant No. 61170113, No.91024001, No.61070142+1 种基金Beijing Natural Science Foundation(No.4111002)KM201010011006, PHR201008242
文摘Internet of Car, resulting from the Internet of Things, is a key point for the forthcoming smart city. In this article, GPS technology, 3G wireless technology and cloud-processing technology are employed to construct a cloud-processing network platform based on the Internet of Car. By this platform, positions and velocity of the running cars, information of traffic flow from fixed monitoring points and transportation videos are combined to be a virtual traffic flow data platform, which is a parallel system with real traffic flow and is able to supply basic data for analysis and decision of intelligent transportation system.
基金supported by the Fundamental Research Funds for the Central Universities (Grant No. CDJZR11170002)the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20090191110022)
文摘By introducing the traffic anticipation effect in the real world into the original lattice hydrodynamic model, we present a new anticipation effect lattice hydrodynamic （AELH） model, and obtain the linear stability condition of the model by applying the linear stability theory. Through nonlinear analysis, we derive the Burgers equation and Korteweg-de Vries （KdV） equation, to describe the propagating behaviour of traffic density waves in the stable and the metastable regions, respectively. The good agreement between simulation results and analytical results shows that the stability of traffic flow can be enhanced when the anticipation effect is considered.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11372166,11372147,61074142,and 11072117)the Scientific Research Fund of Zhejiang Province,China(Grant No.LY13A010005)+1 种基金the Disciplinary Project of Ningbo City,China(Grant No.SZXL1067)the K.C.Wong Magna Fund in Ningbo University,China,and the Government of the Hong Kong Administrative Region,China(Grant No.119011)
文摘In light of previous work [Phys. Rev. E 60 4000 （1999）], a modified coupled-map car-following model is proposed by considering the headways of two successive vehicles in front of a considered vehicle described by the optimal velocity function. The non-jam conditions are given on the basis of control theory. Through simulation, we find that our model can exhibit a better effect as p = 0.65, which is a parameter in the optimal velocity function. The control scheme, which was proposed by Zhao and Gao, is introduced into the modified model and the feedback gain range is determined. In addition, a modified control method is applied to a mixed traffic system that consists of two types of vehicle. The range of gains is also obtained by theoretical analysis. Comparisons between our method and that of Zhao and Gao are carried out, and the corresponding numerical simulation results demonstrate that the temporal behavior of traffic flow obtained using our method is better than that proposed by Zhao and Gao in mixed traffic systems.
基金supported by the Civil Aviation Safety Capacity Building Project.
文摘In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is proposed.On the basis of previous studies,this paper expands the set of weather characteristics affecting the traffic flow in the terminal area,including weather forecast data and Meteorological Report of Aerodrome Conditions(METAR)data.The terminal airspace is divided into smaller areas based on function and the weather severity index(WSI)characteristics extracted from weather forecast data are established to better quantify the impact of weather.MICL model preserves the advantages of the convolution neural network(CNN)and the long short-term memory(LSTM)model,and adopts two channels to input WSI and METAR information,respectively,which can fully reflect the temporal and spatial distribution characteristics of weather in the terminal area.Multi-scene experiments are designed based on the real historical data of Guangzhou Terminal Area operating in typical convective weather.The results show that the MICL model has excellent performance in mean squared error(MSE),root MSE(RMSE),mean absolute error(MAE)and other performance indicators compared with the existing machine learning models or deep learning models,such as Knearest neighbor(KNN),support vector regression(SVR),CNN and LSTM.In the forecast period ranging from 30 min to 6 h,the MICL model has the best prediction accuracy and stability.
