Robust traffic assignment model: Formulation,solution algorithms and empirical application

ABSTRACT

The deterministic traffic assignment problem based on Wardrop's first criterion of traffic network utilization has been widely studied in the literature. However, the assumption of deterministic travel times in these models is restrictive, given the large degree of uncertainty prevalent in urban transportation networks. In this context, this paper proposes a robust traffic assignment model that generalizes Wardrop's principle of traffic network equilibrium to networks with stochastic and correlated link travel times and incorporates the aversion of commuters to unreliable routes.

The user response to travel time uncertainty is modeled using the robust cost (RC) measure (defined as a weighted combination of the mean and standard deviation of path travel time) and the corresponding robust user equilibrium (UE) conditions are defined. The robust traffic assignment problem (RTAP) is subsequently formulated as a Variational Inequality problem. To solve the RTAP, a Gradient Projection algorithm is proposed, which involves solving a series of minimum RC path sub-problems that are theoretically and practically harder than deterministic shortest path problems. In addition, an origin-based heuristic is proposed to enhance computational performance on large networks. Numerical experiments examine the computational performance and convergence characteristics of the exact algorithm and establish the accuracy and efficiency of the origin-based heuristic on various real-world networks. Finally, the proposed RTA model is applied to the Chennai road network using empirical data, and its benefits as a normative benchmark are quantified through comparisons against the standard UE and System Optimum (SO) models.     

基于粗糙集交通信息提取计算的城市道路行程时间预测

针对城市道路的行程时间预测问题进行研究。由于城市道路交通问题具有不确定性和不精确性,故采用基于粗糙集的交通信息提取计算理论建立城市道路行程时间预测模型。模型建立后,利用在荷兰代尔夫特市采集到的实际数据,对该预测模型进行检验。检验结果表明:如果不进行原始数据的前期处理,那么得到的预测误差在35%左右;而在剔除了质量较差的数据后,预测精度明显提高;同时,条件属性和决策属性的分类,显著影响到预测的精度。通过计算得到分类范围值,该模型能够较好的对交通状态进行物理解释同时预测精度能够达到可以接受的范围。     

基于交通流理论的公交站点间行程时间预测

分析了公交站点间车辆运行过程,将行程预测时间划分为交叉口排队等待时间、路段行驶时间和停站时间3个部分,利用交通波理论和延误三角形,分别建立了无公交专用车道和有公交专用车道2种情况下排队等待时间的动态预测模型;根据乘客到站规律和上下车规律,提出了公交车进站停靠时间模型;针对无公交专用车道条件下的时间预测方法进行了实例演算.实验数据表明,基于交通波行程时间预测方法具有较高的精度,可以满足站点间行程时间预报要求.     

The influence of alternative data smoothing prediction techniques on the performance of a two-stage short-term urban travel time prediction framework

This article investigates the impact of alternative data smoothing and traffic prediction methods on the accuracy of the performance of a two-stage short-term urban travel time prediction framework. Using this framework, we test the influence of the combination of two different data smoothing and four different prediction methods using travel time data from two substantially different urban traffic environments and under both normal and abnormal conditions. This constitutes the most comprehensive empirical evaluation of the joint influence of smoothing and predictor choice to date. The results indicate that the use of data smoothing improves prediction accuracy regardless of the prediction method used and that this is true in different traffic environments and during both normal and abnormal (incident) conditions. Moreover, the use of data smoothing in general has a much greater influence on prediction performance than the choice of specific prediction method, and this is independent of the specific smoothing method used. In normal traffic conditions, the different prediction methods produce broadly similar results but under abnormal conditions, lazy learning methods emerge as superior.     

基于多源数据的城市道路网络行程时间预测模型

针对基于单一数据源、利用卡尔曼滤波理论建立行程时间预测模型存在的不足,采用多源数据进行行程时间预测以提高精度。浮动车、固定检测器是常用的交通信息采集方法,在信息种类、数据精度等方面存在一定的互补性。因此,选择2种检测器的实时交通数据作为模型输入参数。利用卡尔曼滤波理论,以流量、占有率、行程时间作为输入量构成参数矩阵,建立城市道路网络行程时间预测模型。并通过Vissim仿真实验验证了模型的有效性。结果表明:基于多源数据的行程时间预测模型平均绝对相对误差为5.45%,其精度比单独采用固定检测器检测数据预测提高了14.4%,比单独采用浮动车数据预测提高了7.5%。      

考虑交通事件影响的城市道路行程时间预测

外部环境因素对城市交通预测有较大影响，尤其在交通事件发生时，由于交通流的随机性和非线性特征，交通异常情况下的预测精度往往较低。为此，基于深度学习理论，提出一种以序列到序列模型（Sequence-to-sequence，Seq2Seq）为主体，融合外部因素特征的城市道路行程时间预测方法。利用时间序列分解算法（Seasonal and Trend Decomposition Using Loess，STL）挖掘交通历史数据的时序周期规律，结合交通事件数据深入分析交通异常产生的原因，并建立堆叠降噪自编码器模型（Stacked Denoising Autoencoder，SDAE）提取时间属性和交通事件数据的潜在特征。以北京市北四环中路和G6京藏高速路段为例，对预测模型的准确性和可行性进行验证，通过重复性交通事件和非重复性交通事件下的案例试验，对SDAE组件的有效性进行分析。研究结果表明：模型的单步和多步预测性能均优于基线模型，预测精度最高达到了87.71%；与其他输入了交通事件数据的模型相比，以SDAE作为外部组件的模型具有较好的预测性能和鲁棒性，能够适应复杂多变的交通流，在智能交通系统的短期预测上有显著的优越性，可以增强管理系统的调控能力，降低城市交通的拥堵成本。     

Subjective-utility travel time budget modeling in the stochastic traffic network assignment

ABSTRACT

In this article, we propose a new model called subjective-utility travel time budget (SU-TTB) model to capture travelers' risk-averse route choices. In the travel time budget (TTB) and mean-excess travel time (METT) model, a predefined confidence level is needed to capture the risk-aversion in route choice. Due to the day-to-day route travel time variations, the exact confidence level is hard to be predicted. With the SU-TTB model, we assume travelers' confidence level belongs to an interval that they may comply with in the route choice. The two main components of SU-TTB are the utility function and the TTB model. We can show that the SU-TTB can be reduced to the TTB and METT model with proper utility function for the confidence levels. We can also prove its equivalence with our recently proposed nonlinear-expectation route travel time (NERTT) model in some cases and give some new interpretation on the NERTT with this equivalence. Finally, we formulate the SU-TTB model as a variational inequality (VI) problem to model the risk-averse user equilibrium (RAUE), termed as generalized RAUE (GRAUE). The GRAUE is solved via a heuristic gradient projection algorithm, and the model and solution algorithm are demonstrated with the Braess's traffic network and the Nguyen and Dupuis's traffic network.     

Travel mode identification using bluetooth technology

Bluetooth technology has been widely used in transportation studies to collect traffic data. Bluetooth media access control (MAC) readers can be installed along roadways to collect Bluetooth-based data. This data is commonly used to measure traffic performance. One of the advantages of using Bluetooth technology to measure traffic performance is that travel time can be measured directly with a certain level of error instead of by estimation. However, travel time outliers can commonly be observed due to different travel mode on arterials. Since travel mode information cannot be directly obtained from the raw Bluetooth-based data, a mathematical methodology is in need to identify travel mode. In this study, a genetic algorithm and neural network (GANN)-based model was developed to identify travel mode. GPS-enabled devices were used to collect ground truth travel time. In order to additionally compare the model performance, K nearest neighbor (KNN) and support vector machine (SVM) were also implemented. N-fold cross validation was applied to statistically assess the models’ results. Since the model performances depend on the model inputs, seven collections of model inputs were tested in order to achieve the best travel mode identification performance. An arterial segment with four consecutive links and three intersections was selected to be the study segment. The results suggested that correctly identifying the three travel modes successfully every time was not possible, although the GANN based model had low misidentification rates. In our study, 6.12% of autos were misidentified as bikes and 10.53% of bikes were misidentified as autos using three links.     

基于非参数回归的快速路行程速度短期预测算法

基于北京市快速路上的检测器所采集的历史数据，经过数据筛选，剔除判别，小波滤噪平稳处理，聚类分析等过程，建立了交通状态演变系列的历史样本数据库。基于所构建的历史数据库，通过数值试验，确定了状态向量、距离匹配原则，K近邻值等参量，构建了一种基于K近邻的非参数回归短时交通预测模型，实现了对路段行程速度的短时预测。最后，利用随机选取的历史数据系列对预测模型的精度进行了检验。结果表明，预测算法的精度可以达到90％以上，可以很好地满足ITS应用系统对于交通预测数据的精度要求。     

车路协同条件下智能网联汽车一体化决策模型

为了探索当前有限数据条件下面临的无限交通场景问题,提出车路协同条件下基于深度强化学习智能网联汽车决策模型。利用Actor-Critic机制,以highway-env为数据来源,抽取144 h交通数据作为训练数据并进行验证,分析了智能网联汽车在不同车道数条件下的驾驶行为。结果显示,本模型汽车行程时间减少20%以上,碰撞概率减少25%以上,换道轨迹可以通过动力学跟踪。     

城市交通流诱导系统中的路段行程时间间接预测方法研究

在阐述综合路段行程时间间接预测模型思想的基础上，提出了基于排队论及基于交通模拟的行程时间间接预测模型，并按照人工调查数据验证模型的精度，给出了相对误差图，以说明模型算法的有效性。     

基于径向基函数神经网络的城市道路路段行程时间实时预测模型

提出利用径向基函数（RBF）神经网络方法对城市道路路段行程时间进行建模NN,并结合线圈和视频实测数据进行仿真分析,以实际行程时间和模型输出的行程时间预测值比较验证了模型的合理性。并将RBF神经网络方法与BP神经网络方法进行比较,结果表明RBF神经网络相对于BP神经网络训练时间短,且预测精度更高。     

路径行程时间的组合预测方法研究

立足于历史和实时数据的融合应用,从实际应用角度出发,构筑了一种路径短时行程时间的组合预测模型和相应算法。该组合预测模型包含基于历史数据特征向量的聚类分析子模型和基于路径行程时间序列的自回归子模型,通过贝叶斯概率公式实现子模型的权重分配。并对数据进行滚动式处理,实现权重系数的实时更新。最后选择上海市快速路系统3条典型路径进行实例分析,并与实际牌照自动识别行程时间数据进行对比验证。     

基于实时交通信息的行程时间估算及路径选择分析

路段行程时间的估计和预测是诱导系统的关键技术之一。由于路网参数不断变化,路段行程时间的估计必须满足实时性的要求。以城市交通控制系统的基本设施为基础,根据我国城市交通目前的发展状况,分析了影响路段行程时间的各种因素和路段行程时间的组成。利用设置在路段上的车辆自动检测装置搜集到的实时交通流信息,并结合随机服务系统的相关理论建立了城市道路路段行程时间的动态计算模型,提出了一种具有真实最短路径意义的实时动态最短路径选择的方法。     

A novel arterial travel time distribution estimation model and its application to energy/emissions estimation

Arterial travel time information is crucial to advanced traffic management systems and advanced traveler information systems. An effective way to represent this information is the estimation of travel time distribution. In this paper, we develop a modified Gaussian mixture model in order to estimate link travel time distributions along arterial with signalized intersections. The proposed model is applicable to traffic data from either fixed-location sensors or mobile sensors. The model performance is validated using real-world traffic data (more than 1,400 vehicles) collected by the wireless magnetic sensors and digital image recognition in the field. The proposed model shows high potential (i.e., the correction rate are above 0.9) to satisfactorily estimate travel time statistics and classify vehicle stop versus non-stop movements. In addition, the resultant movement classification application can significantly improve the estimation of traffic-related energy and emissions along arterial.     

Predicting arterial breakdown probability: A data mining approach

Predicting the probability of traffic breakdown can be used as an important input for creating advanced traffic management strategies that are specifically implemented to reduce this probability. However, most, if not all, past research on the probability of breakdown has focused on freeways. This study focuses on the prediction of arterial breakdown probability based on archived traffic data for use in real-time transportation system operations. The breakdown of an arterial segment is defined in this study as a segment's operating condition under the level of service F according to the highway capacity manual threshold, although any other level of service could be used. Data from point detection and automatic vehicle identification matching technologies are aggregated in space and time to allow their use as inputs to the prediction model. A decision tree approach, combined with binary logistic regression, is used in this study to predict the breakdown probability based on these inputs. The model is validated using data not used in the development of the model. The research shows that the root mean square error and the mean absolute error of the prediction was 13.6 and 11%, respectively. The analysis also shows that the best set of parameters used in the prediction can be different for different links, due to the various causes of breakdown and characteristics of different links. Predicting the probability of breakdown in ahead of time will allow the agencies to change the signal-timing plan that can delay or eliminate the breakdown.     

观测路径出行时间下随机网络交通需求估计

道路网络起讫点（OD）需求是城市决策长期交通规划和短期交通管理中的基础参数,准确的交通需求更是实施交通拥堵控制、限行限速、路径诱导等措施的先决条件。综合运用观测的轨迹已知和未知路径出行时间,建立随机网络交通需求估计双层规划模型。上层广义最小二乘模型最小化历史交通需求与待估交通需求、观测路径出行时间与待估路径出行时间之间的偏差,约束为交通需求、路段流量、路段出行时间与路径出行时间之间的传播关系,通过高斯混合模型（GMM）对其中轨迹未知的观测出行时间依概率聚类。下层为随机网络交通出行均衡模型,分别运用出行时间预算和随机用户均衡处理路网不确定性和出行者感知误差。上、下层之间通过交通需求和OD-路段关联比例进行信息传递。设计迭代算法框架求解双层规划模型,迭代算法包含求解上层模型的最速下降法、求解下层模型的相继平均算法和求解GMM模型的最大期望（EM）算法。通过算例表明轨迹未知的路径出行信息的加入在提升需求估计精度的同时也增大了估计值的方差;设计的迭代算法能够稳定收敛到10^-5的精度;GMM软聚类方法估计的交通需求显著优于硬聚类方法估计的需求值;交通需求值对观测路径出行时间的扰动更加敏感。研究考虑出行者风险态度,通过轨迹信息的重新构建揭示城市交通需求演化规律。     

一种新的城市快速路行程时间预测技术

根据城市快速路交通诱导和监控系统的实际需要,提出了基于宏观动态流体力学模型的行程时间预测技术,可以动态预测稳定流和非稳定流状况下城市快速路网上任意两点间行程时间.     

基于改进SWF神经网络多因素行程时间预测模型与算法

行程时间预测一直是交通领域研究的重点问题之一,道路系统的复杂性使预测工作变得困难。将影响路段行程时间的多种因素和改进后的样条权函数神经网络结合起来,根据机动车运行特点,建立行程时间预测模型,可以刻划道路运行的多种状态,能较准确的估计出路段的行程时间,也继承了样条权函数神经网络算法的各种优点。     

基于数据预测的区域道路状态模糊判别

区域路网交通状态判别是实施区域交通管理控制和交通诱导的基础。为有效且有前瞻性地描述区域路网拥挤状况,提出了1种基于时间序列数据预测和主成分分析相结合的模糊综合定量评价方法。以路段平均速度和交通流量为描述交通拥挤状况的参数,利用时间序列预测模型对数据进行预测;将路网中各路段的平均旅行时间作为总延误的影响因素;再利用主成分分析法确定各个路段对区域拥挤的影响权重;最后运用模糊综合评价法对区域路网拥挤状况进行评估。以山西省临汾市实际路网为例,通过 Vissim 交通仿真软件和 SPSS 数据统计分析软件对算法进行了仿真验证。仿真结果表明,该算法能够有效地预判城市区域的交通状况,为交通管理、控制和诱导提供准确的依据。