一种交通拥堵指数智能计算方法

交通拥堵与许多因素密切相关,具有强烈的随机性、偶然性,导致当前交通拥堵指数计算误差大,可靠性差等问题,为了提高交通拥堵指数计算精度,提出了基于支持向量机的交通拥堵指数智能计算方法。先分析当前交通拥堵指数智能计算的研究进展,找到引起交通拥堵指数计算效果的原因,然后采集一段时间的交通拥堵指数序列,引入支持向量机对交通拥堵指数序列进行建模与分析,找到交通拥堵指数变化规律,最后采用具体仿真实验与其它交通拥堵指数智能计算方法进行了对照实验。结果表明,这种方法降低了交通拥堵指数计算误差,为可以为交通管理者提供有价值的信息,有利于缓解交通拥堵问题,具有比较明显的优越性。     

基于协调博弈的交通拥塞传播临界值研究

为深入分析交通网络的拥塞扩散过程,得出交通拥塞传播的临界值,提出了交通拥塞传播的协调博弈模型。通过网络个体之间的协调博弈,从出行者面对拥塞的决策行为出发,描述了交通网络的拥塞扩散过程。通过网络邻居之间的行为传递,形成了交通网络的拥塞扩散模型,并利用概率母函数方法推导了交通拥塞扩散的临界条件。最后构建了交通通塞的仿真系统,并通过路网结构、节点度分布等参数对交通拥塞进行了仿真分析。仿真实验结果与解析分析结果一致,并能反映交通拥塞动态过程信息,结果表明交通拥塞扩散的临界条件关键在于拥塞节点对周边正常节点的影响力,当局部交通拥塞对周边节点的影响力达到一定程度时,可能导致大规模交通拥塞的出现。     

基于改进DV-HOP的道路交通拥堵传感节点快速监测

由于现有交通拥堵监控设备在海量三维交通信息中处理数据的能力较差,导致监测目标延迟较高,故设计一种基于改进DV-HOP的道路交通拥堵传感节点快速监测方法;在待监测区域安置无线视觉传感器,划分子节点与Sink节点,采集车辆通行状况和整体长度;把异常道路数据作为小概率事件,确立速率采集周期及交通状态采集周期,推算历史车辆速率均值和交通数据方差,设定拥堵临界值,分析路段是否产生拥堵;对道路交通拥堵节点进行初始化,确定全部道路交通拥堵节点,并将其转换到二维坐标中;利用改进DV-HOP算法获取道路交通拥堵节点位置信息,得出道路交通拥堵节点监测结果;实验分析表明：设计方法的均等系数值可达0.998,数据传输延时仅为3.5 s,表明交通拥堵监测精度较高。     

车联网环境下基于模糊逻辑的交通拥堵检测方法

针对现有的道路交通拥堵检测方法的不足,提出了一种基于V2V的道路交通拥堵检测方法。首先基于V2V的方式实时获取邻居车辆状态信息,建立车辆邻居表;其次依据车辆行驶速度、车流密度、交通拥堵评级体系构建模糊控制器,完成本地交通拥堵水平的估计;然后通过车车通信进行邻居车辆交通拥堵状况的查询,并根据大子样假设检验验证本地交通拥堵水平值,完成所在区域交通拥堵水平的检测;最后基于Veins平台搭建仿真测试场景,仿真对比了拥堵检测结果的准确率,同时测试车辆节点的退避时槽数量和接收广播数据包的数量。实验结果表明, 提出的道路交通拥堵检测方法实现的拥堵检测准确率分别比线圈法和CoTEC法提高了5.5%和7.5%;提出的道路交通拥堵检测方法实现的车车通信网络拥塞比CoTEC法降低了90.8%,并且在未发生交通拥堵时通信节点的通信负载显著降低。     

基于CA模型的上坡道小汽车-卡车交通拥堵特性

研究上坡道时小汽车和卡车组成的异质交通流的特点,将卡车分为重车和空车,使用的模型是一个更为精细的基于安全驾驶的元胞自动机（CA）模型,并通过计算机数值模拟分析了不同的坡度和坡道长度下异质交通流的特征。研究得出如下的结论：上坡道会明显改变交通流特征,交通流由之前分散的阻塞带变化为多个密集的短阻塞带,并且主要集中于坡道上和坡道前段,交通拥堵显著增加,40?m长的坡道就会增加近10%的拥堵;低密度情况下,卡车加入会在一定程度上缓解拥堵,重车缓解的程度更高,高密度情况下,卡车对于拥堵比例的影响较小;交通流的拥堵比例随着纵坡度的增大而增大,这说明减少纵坡度能够缓解拥堵;此外,当坡道纵坡度一定时,可以通过适当加大坡道长度而达到减缓拥堵的效果。     

增量式贝叶斯分类器在交通拥堵判别中的应用

为有效发现道路交通拥堵状态,提出基于增量式贝叶斯分类器的交通拥堵判别方法.该方法把交通拥堵是否发生看成是特殊的分类问题,选取增量式贝叶斯分类器,根据以往是否发生交通拥堵的检测数据,即分别把在发生交通拥堵和不发生交通拥堵两种情况下的交通参数作为特征参数对其进行训练,然后用得到的分类器对检测到的交通参数进行分类,判别是否发生交通拥堵.微观交通仿真数据表明该方法的可行性和有效性.     

Vehicle routing under time-dependent travel times: The impact of congestion avoidance

Daily traffic congestion forms a major problem for businesses such as logistic service providers and distribution firms. It causes late arrivals at customers and additional costs for hiring the truck drivers. Such costs caused by traffic congestion can be reduced by taking into account and avoiding predictable traffic congestion within vehicle route plans. In the literature, various strategies are proposed to avoid traffic congestion, such as selecting alternative routes, changing the customer visit sequences, and changing the vehicle-customer assignments. We investigate the impact of these and other strategies in off-line vehicle routing on the performance of vehicle route plans in reality. For this purpose, we develop a set of vehicle routing problem instances on real road networks, and a speed model that reflects the key elements of peak hour traffic congestion. The instances are solved for different levels of congestion avoidance using a modified Dijkstra algorithm and a restricted dynamic programming heuristic. Computational experiments show that 99% of late arrivals at customers can be eliminated if traffic congestion is accounted for off-line. On top of that, about 87% of the extra duty time caused by traffic congestion can be eliminated by clever congestion avoidance strategies.     

基于神经网络的城市快速路交通拥堵判别算法

针对城市快速路的常发性拥堵和偶发性交通拥堵,提出了一种基于神经网络的自动判别算法.该方法利用改进的自适应梯度算法优化神经网络的权值参数,既能保证神经网络参数收敛到全局最优值,又具有快的学习速度,提高了神经网络的检测效果.利用微观交通仿真软件PARAMICS建立了城市快速路网,通过多次仿真获得了包含各种交通拥堵的学习样本,增强了算法的鲁棒性.将训练好的神经网络对多种实际的交通数据进行了仿真试验.实验结果表明,该算法在城市快速路交通拥堵判别中具有较高的检测率和较低的误报率.     

空中交通流量管理方法初探

空中交通管理是为解决空中交通拥挤而进行的系统化管理,文中介绍了空中交通流量管理的基本概念,并进行了流量管理方法的初探,同时提出了改善流量拥挤现状的环境和合理化建议。     

Urban traffic congestion estimation and prediction based on floating car trajectory data

Traffic flow prediction is an important precondition to alleviate traffic congestion in large-scale urban areas. Recently, some estimation and prediction methods have been proposed to predict the traffic congestion with respect to different metrics such as accuracy, instantaneity and stability. Nevertheless, there is a lack of unified method to address the three performance aspects systematically. In this paper, we propose a novel approach to estimate and predict the urban traffic congestion using floating car trajectory data efficiently. In this method, floating cars are regarded as mobile sensors, which can probe a large scale of urban traffic flows in real time. In order to estimate the traffic congestion, we make use of a new fuzzy comprehensive evaluation method in which the weights of multi-indexes are assigned according to the traffic flows. To predict the traffic congestion, an innovative traffic flow prediction method using particle swarm optimization algorithm is responsible for calculating the traffic flow parameters. Then, a congestion state fuzzy division module is applied to convert the predicted flow parameters to citizens’ cognitive congestion state. Experimental results show that our proposed method has advantage in terms of accuracy, instantaneity and stability.     

交通拥挤控制的实时决策支持模型

针对交通拥挤的快速检测和控制问题,设计了一种基于管理者知识和经验,能够实时反映交通拥挤状况的决策支持模型．设计的自动决策支持模型中包含了概念模型和推理模型,推理模型中集成了交通拥挤自动检测算法和拥挤交通量控制方案选择的模糊推理算法．研究结果表明,采用自动决策支持模型能在一定程度上取代交通管理者对拥挤的管理,从而提高拥挤管理的效率和决策质量．     

Design of Regulatory Traffic Light Control Systems with Synchronized Timed Petri Nets

Fixing the phases is one of the common methods to control an urban traffic network. Once a road is filled with a high traffic flow approaching its capacity, the conventional traffic light controller is not able to handle this traffic congestion phenomenon well. In this paper, we propose a novel regulatory traffic light control system to handle such traffic congestion by using synchronized timed Petri nets (STPNs). Three kinds of intersections in an urban traffic network are defined and employed to demonstrate our new regulatory traffic light control system models. Finally, the liveness and reversibility of the proposed STPN models are proven through the reachability graph analysis method. To our knowledge, this is the first work that solves a traffic congestion problem with a regulatory traffic light control technique that is effective in preventing vehicles from entering traffic congestion zones.     

Traffic congestion analysis at the turn level using Taxis' GPS trajectory data

Sensing turn-level or lane-level traffic conditions not only enables navigation systems to provide users with more detailed and finer-grained information, it can also improve the accuracy in the search for the fastest routes and in short-term predictions of traffic conditions. The widespread collection and application of taxis' GPS data enable us to sense urban traffic flow on a large scale. Since current GPS positional accuracy cannot reach the lane level, existing approaches using GPS trajectory data only analyze traffic conditions at the road level. Whereas some studies attempted to detect lane-level traffic conditions using lane-level data, the high cost of data collection considerably limits their practical application. To address this limitation, this article proposes an approach for detecting traffic congestion from taxis' GPS trajectories at the turn level. Based on analyzing features of GPS trajectories and identifying valid trajectory segments, the proposed approach detects congested trajectory segments of three different intensities. It then identifies congestion events in each turning direction through a clustering approach. Finally, congestion intensity, time of the day when congestion occurred and queue length in each turning direction at a road intersection in Wuhan, China are explored and analyzed. The results support the feasibility of this approach for detecting and analyzing traffic congestion at the turn level. Compared with other approaches that detect traffic congestion using GPS trajectory data, the proposed approach analyzes congestion at a finer-grained level (the turn level). Compared with other approaches that detect traffic congestion at the lane level, the proposed approach can sense traffic congestion over a larger area and at a lower cost.     

Urban traffic congestion propagation and bottleneck identification

Bottlenecks in urban traffic network are sticking points in restricting network collectivity traffic efficiency. To identify network bottlenecks effectively is a foundational work for improving network traffic condition and preventing traffic congestion. In this paper, a congestion propagation model of urban network traffic is proposed based on the cell transmission model （CTM）. The proposed model includes a link model, which describes flow propagation on links, and a node model, which represents link-to-link flow propagation. A new method of estimating average journey velocity （AJV） of both link and network is developed to identify network congestion bottlenecks. A numerical example is studied in Sioux Falls urban traffic network. The proposed model is employed in simulating network traffic propagation and congestion bottleneck identification under different traffic demands. The simulation results show that continual increase of traffic demand is an immediate factor in network congestion bottleneck emergence and increase as well as reducing network collectivity capability. Whether a particular link will become a bottleneck is mainly determined by its position in network, its traffic flow （attributed to different OD pairs） component, and network traffic demand.     

不完全数据下基于时空相关性拥堵预测方法

交通拥堵预测是智慧交通一个重要组成部分,但是大量的交通数据无法以公开的方式获取。在不完全数据下,提出了一种基于时空相关性的交通拥堵预测方法。该方法采用改进的核密度估计法,使得预测过程中不依赖大量历史数据进行训练,直接利用部分采集到的数据精准地实时地对交通拥堵进行预测。在真实数据集上对提出的交通拥堵预测方法进行验证,实验结果表明了该方法在实时交通预测上的可行性。     

基于时空势场修正多处理器城市拥堵并行聚类分析

为提升城市城市道路拥堵检测和治理效率,提出一种基于势场修正多处理器并行聚类的城市道路拥堵时空分析方法。首先,利用GIS四维空间时态数据给出城市道路拥堵的时空模型,并通过设置虚拟数据参数实现时间的低密度采样处理,获得城市道路拥堵路段时空规律性的有效检测;其次,基于势场修正法构建多处理器并行聚类方法,分别设计了距离矩阵、邻域半径和密度函数的并行化多处理计算方法,并实现了并行聚类算法设计,同时给出上述并行计算过程的计算复杂度分析定理;最后,以北京市为试验区,对所提城市道路拥堵分析算法性能进行了验证,实验结果表明,所提方法可实现城市城市道路拥堵情况的快速有效检效检测分析,可为城市道路拥堵管理提供数据支撑。     

不同信息共享程度下交通拥塞控制研究

信息共享程度是影响交通通行效率的重要条件。分析了信息闭塞、局部信息共享和全局信息共享三种信息共享模式下的交通拥塞现象及其传播特征,并对网络节点行为进行动力学分析,采用概率母函数、分支过程和协调博弈的方法建立了交通拥塞传播模型,解析分析了交通拥塞传播的临界值,比较了不同信息共享模式下的交通拥塞控制策略。仿真实验表明,信息闭塞和局部信息共享下的拥塞控制在交通网络流量较小时更为有效,全局信息共享有利于抑制大规模的拥塞传播,但其可控难度较大。     

对网络流量管理与拥塞管理的研究

分析了计算机网络拥塞产生的原因及影响,研究了网络流量管理与拥塞管理的策略,提出了采用流量管理技术来增强网络层的流量控制功能,控制网络拥塞的产生,采用拥塞管理策略,优化网络资源的分配,解决网络资源的竞争,为有不同服务需求的网络业务提供有区别的服务,从而有效地控制网络拥塞。     

交通灯运行时间自适应算法及其控制系统

城市交通拥堵具有严重的危害性, 直接导致时间延误、能源浪费和废弃物排放增加, 降低居民生活水平. 现阶段, 基于平面交叉路口交通灯切换时间相对固定, 恶劣天气或发生交通事故时路口经常发生交通堵塞的实际情况, 本文提出了一种平面交叉口交通拥堵多方向交通灯运行时间自适应算法, 采取视频图像处理算法判断道路交通拥堵情况, 根据路况设置交通灯的工作时间, 并设计了相应的控制系统. 仿真结果表明, 在高峰期时段, 此自适应算法的车辆通行效率高于传统的交通灯运行时间控制方法.     

Traffic conduction analysis model with time series rule mining

The traffic density situation in a traffic network, especially traffic congestion, exhibits characteristics similar to thermodynamic heat conduction, e.g., the traffic congestion in one section can be conducted to other adjacent sections of the traffic network sequentially. Analyzing this conduction facilitates the forecasting of future traffic situation; therefore, a navigation system can reduce traffic congestion and improve transportation mobility. This study describes a methodology for traffic conduction analysis modeling based on extracting important time-related conduction rules using a type of evolutionary algorithm named Genetic Network Programming (GNP). The extracted rules construct a useful model for forecasting future traffic situations and analyzing traffic conduction. The proposed methodology was implemented and experimentally evaluated using a large scale real-time traffic simulator, SOUND/4U.