Estimation of Traffic Demand at Freeway Work Zones

An iterative process,combining a macroscopic simulator and a set of the traffic demand-change estimation models,is developed to estimate the traffic demand at work zones in urban freeway corridors.The process is designed to capture the interaction between work-zone conditions and traffic diversion in determining the traffic demand approaching the entrance and exit ramps at a given work zone.The proposed models and process were calibrated and tested with the field data from the work zones in the Minnesota metro-freeway network.The test results indicate promising possibilities of the proposed process in terms of the estimation accuracy and transferability of the demand-change estimation models developed in this study.

Tourism Traffic Demand Prediction Using Google Trends Based on EEMD-DBN

Predicting tourism traffic demand accurately plays an important role in making effective policies for tourist administration. It helps to distribute the resources reasonably and avoid the tourism congestions. This paper considered the noise interference and proposed a hybrid model, combining ensemble empirical mode decomposition (EEMD), deep belief network (DBN) and Google trends, for tourism traffic demand prediction. This model firstly applied dislocation weighted synthesis method to combine Google trends into a search composite index, and then it denoised the series with EEMD. EEMD extracted the high frequency noise from the original series. The low frequency series of search composite index would be used to forecast the low frequency tourism traffic series. Taking the inbound tourism in Shanghai as an example, this paper trained the model and predicted the next 12 months tourism arrivals. The conclusion demonstrated that the forecast error of EEMD-DBN model is lower remarkably than the baselines of ARIMA, GM(1,1), FTS, SVM, CES and DBN model. This revealed that nosing processing is necessary and EEMD-DBN forecast model can improve the prediction accuracy.

TransCAD and GIS Technique for Estimating Traffic Demand and Its Application in Gaza City

In the early nineties of the last century, the transportation system in Gaza Strip was born and new infrastructure projects, especially road networks, were constructed. However, the construction lacked efficient application of a transportation planning process. Transportation planning relies on traffic demand forecasting process. The conventional process is impeded by extensive amount of socioeconomic data. One of the most widely-used models which mitigate this problem is the TransCAD Model. This model is rarely used in Gaza Strip for traffic demand forecasting, and most of the practices depend mainly on a constant growth rate of traffic. Therefore, the main objective of this research is to apply this model in Gaza City for traffic estimation. This model estimates the origin-destination matrix based on traffic count. The traffic count was carried out at 36 intersections distributed around Gaza City. The results of traffic flow estimation obtained from TransCAD are assigned to the Gaza maps using the GIS techniques for spatial analysis. It is shown that the most congested area at present is the middle of the city especially at Aljala-Omer Almokhtar intersection. Therefore, improvement scenarios of this area should be carried out. The results of calibration of traffic flow estimation show that the differences between the estimated and the actual flows were less than 10%. In addition, network evaluation results show that the network is expected to be more congested in 2015. This work can be used by transportation planners for testing any network improvement scenarios and for studying their network performance.

Fair multigroup multicast precoding design based on traffic demands for multibeam satellite systems

Onboard resources are limited for multibeam satellite communication systems,while differences exist in traffic demands among users.Since conventional multigroup multicast precoding methods do not take traffic demands for users into consideration,it is difficult to flexibly adjust the offered throughput to users’demands.Users with higher demand may obtain lower throughput while users with lower demand may be over-satisfied,which results in the requested-offered throughput mismatch and resource waste.This paper proposes a fair multigroup multicast precoding design based on traffic demands.To obtain the precoding design,the optimization problem aimed at maximizing the minimum throughput satisfaction ratio,which is defined as the ratio of the offered throughput to the traffic demand,is formulated,so as to provide fair service for all users while satisfying per-feed power constraints and traffic demand constraints.To address this problem,an auxiliary variable is first introduced to equivalently simplify it.Then,the semidefinite relaxation and the bisection search strategies are adopted to further handle the problem.Finally,the optimal precoding vectors are obtained by employing eigenvalue decomposition or Gaussian randomization.Simulation results indicate the effectiveness of the proposed precoding algorithm and demonstrate that it can better adapt to the scenarios with different traffic demands.

Scheme design technique for urban traffic management planning

Management tactics for urban traffic management are presented.The tactics that underlie traffic demand management （TDM） are preferential development tactics, controlled development tactics,prohibited development tactics and economic lever tactics,and those that underlie traffic system management （TSM） are node traffic management tactics,arterial traffic management tactics and area traffic management tactics.The specific contents and design methods of urban traffic total demand control,urban traffic structure optimization,road traffic movement organization based on TDM and intersection traffic management,road signs and markings management,optimized design of traffic signals and management of parking spaces based on TSM are put forward.The urban traffic management planning scheme design method has already been used in the urban traffic management “Smooth Traffic Project” in China.

面向动态交通分配的交通需求深度学习预测方法

为满足动态交通分配对高精度、高时效性交通需求的要求,本文建立了一种交通需求深度学习预测方法。根据动态交通分配要求确定交通需求数据的时间间隔,构建对复杂交通需求预测性能较优的长短期记忆神经网络预测方法;针对动态交通分配中交通需求的周期性、随机性和非线性等特征,为减少数据噪声的干扰,引入局部加权回归周期趋势分解方法将交通需求数据分解,将其中的趋势分量和余项分量作为深度学习预测方法的输入量,周期分量采用周期估计进行预测;选用具有随机寻优能力强、寻优效率高等特点的布谷鸟寻优算法优化预测方法的隐藏层单元数量、学习速率和训练迭代次数等核心参数。应用西安市长安区的卡口车牌数据验证该方法。结果表明:本文模型的预测结果在高峰及平峰各连续4个时段内相比于自回归滑动平均模型、长短期记忆神经网络模型、支持向量回归模型,平均绝对误差降低了10.55%~19.80%,均方根误差降低了11.20%~17.99%,决定系数提升了8.62%~12.48%;相比遗传算法、粒子群算法优化的模型,平均绝对误差降低了7.36%~13.81%,均方根误差降低了4.23%~10.67%,决定系数提升了3.50%~7.01%,且本文模型运行时间最短。说明与对比模型相比,本文所建立的预测方法在面向动态交通分配的交通需求预测中具有更高的预测精度。

Resilience assessment and optimization method of city road network in the post-earthquake emergency period

The post-earthquake emergency period,which is a sensitive time segment just after an event,mainly focuses on saving life and restoring social order.To improve the seismic resilience of city road networks,a resilience evaluation method used in the post-earthquake emergency period is proposed.The road seismic damage index of a city road network can consider the influence of roads,bridges and buildings along the roads,etc.on road capacity after an earthquake.A function index for a city road network is developed,which reflects the connectivity,redundancy,traffic demand and traffic function of the network.An optimization model for improving the road repair order in the post-earthquake emergency period is also developed according to the resilience evaluation,to enable decision support for city emergency management and achieve the best seismic resilience of the city road network.The optimization model is applied to a city road network and the results illustrate the feasibility of the resilience evaluation and optimization method for a city road network in the post-earthquake emergency period.

基于需求层次理论的城市公共交通发展战略研究

针对目前城市交通供需结构不平衡的问题,以马斯洛需求层次理论模型为参考,结合城市交通需求和供给特性,分析其供求关系及层次结构,提出城市交通供需的响应关系和理想化城市交通出行结构。考虑时间、经济、舒适度等交通需求因素和环境、运营、基础设施、能耗等交通供给资源,以现状需求、资源、环境污染、运营、发展规模、时间为约束,从宏观和微观两个角度构建双层规划模型。以大连市为研究对象,基于现有交通出行结构开展成本分析,计算现有出行需求情况下,大连市城市交通结构的适宜比例,并将计算结果与现有出行结构进行比较。研究表明,优化的出行结构可以更好地满足现有城市交通的出行需求,满足城市交通可持续发展的目标,研究结果可为今后大连市公共交通发展提供参考。

低客流公交运营模式优化方法

为解决低客流传统公交线路运营效率低的问题,考虑低客流公交线路客流时空特性,提出了采用传统公交与需求响应公交(demand response transit,DRT)相结合的组合运营模式:全时段传统公交模式(M1)、分时段传统公交+DRT模式(M2)全时段DRT模式(M3)的优化思路。分析了不同运营模式的要素,考虑乘客空间、时间特征,构建基于三维时空聚类的站点规划模型;考虑车辆行驶成本、乘客时间成本,以总班次运营成本最小为目标,构建了带有时间窗的灵活型DRT线路与调度规划模型,运用遗传算法进行求解。以北京市某公交线路进行仿真实证,仿真结果表明:M2相比M1、M3分别降低了9.0%、23.0%的运营成本。研究可针对低客流公共交通服务的运营方案制定与优化提供技术参考。

计及道路交通指数影响的公交充电站充电桩优化配置方法

当前中国大力推动城市公交车全面电动化,优化配置充电桩是公交充电站建设的关键。文中提出了计及道路交通指数影响的公交充电站充电桩优化配置方法,首先,综合考虑公交线路交通专用道启用时段和季节性附加能耗,提出了基于道路交通指数的充电桩优化配置模型的典型运行场景提取方法,构建了基于公交线路交通指数的公交车能耗模型;然后,综合考虑规划周期内充电桩配置成本和充电站日充电成本,构建了公交充电站充电桩配置双层优化模型,并设计了基于列生成算法的高维混合整数规划模型求解方法;最后,以某待建公交车充电站为算例开展了有效性验证。结果表明,所提方法得到的配置方案可同时满足接入点配电容量限制和公交通勤要求,并提升充电站运营经济性。

基于多尺度时空图卷积网络的交通出行需求预测

满足公众高质量出行需求是智能交通系统(ITS)的主要挑战之一。目前,针对公共交通出行需求预测问题,现有模型大多采用固定结构的图描述出行需求的空间相关性,忽略了出行需求在不同尺度下具有不同的空间依赖关系。针对上述问题,提出一种多尺度时空图卷积网络(MSTGCN)模型。该模型首先从全局尺度和局部尺度构建全局需求相似图和局部需求相似图,这2种图可以捕获公共交通出行需求长期内较为稳定的全局特征和短期内动态变化的局部特征。利用图卷积网络(GCN)提取2种图中的全局空间信息和局部空间信息,并引入注意力机制融合两种空间信息。为了拟合时间序列中潜藏的时间依赖关系,利用门控循环单元(GRU)捕捉公共交通需求的时变特征。采用纽约市出租车订单数据集和自行车订单数据集进行实验,结果表明MSTGCN模型在自行车订单数据集上均方根误差(RMSE)、平均绝对误差(MAE)和皮尔逊相关系数(PCC)达2.7886、1.7371、0.7992,在出租车订单数据集上RMSE、MAE、PCC达9.5734、5.8612、0.9631。可见,MSTGCN模型可以有效地挖掘公共交通出行需求的多尺度时空特性,对未来公共交通出行需求进行准确预测。

基于不确定需求的集中式充电站分级选址鲁棒优化研究

以集中式充电站为研究对象,采用多面体不确定集描述不同用地性质下异质充电需求的不确定性,考虑运营商和用户双方利益,构建以建设运营成本、充电成本和寻站成本最优为目标,充电距离和充电需求等约束协同的鲁棒优化模型,并通过Bertsimas和Sim鲁棒对等转换,将半无限优化模型转换成易于求解的0~1整数规划问题。数值仿真结果表明:首先,集中式充电站选址不确定水平因素发生变化时,系统成本呈现阶梯式上升,并且建设运营成本对系统成本影响最为显著;其次,充电需求变化幅度越小,模型鲁棒性越高,集中充电设施选址适应度越高,充电站建设运营商根据自身的风险偏好程度选择不同参数组合,实现在异质需求下集中式充电站充电需求与社会总成本的平衡,获得充电站选址的科学方案;最后,对比分析不同情景下的充电站设置方案验证模型有效性。

机场航班时刻资源管理研究进展

繁忙机场都会面临严重的交通拥堵和航班延误问题。解决该问题的一个有效手段是对机场航班时刻资源进行优化管理。全面介绍了航班时刻资源管理相关的研究进展,系统回顾了机场公布容量设置、机场航班时刻配置的主要方法和手段。从公布容量确定、单机场、机场网络层面和机场群航班时刻配置及航班时刻配置技术复杂性等方面,得出机场航班时刻资源优化配置的关键技术问题。展望了机场航班时刻资源管理的主要方向,并对下一步研究提出建议。

精细化治理背景下的交通限行区分级管控合理性评估与优化——以杭州市为例

合理地划定限行区域,辅之以差异化的交通需求管理政策能够有效缓解城市拥堵、精准提升城市交通治理水平。以实时交通拥堵指数、OSM路网数据、公交线路和站点数据为研究数据,识别杭州市分级限行区内的拥堵区分布,分析拥堵区交通供给特征,在此基础上划分拥堵区类型并提出分类管控优化策略。研究发现,杭州市限行区分级较为合理,对浙A及区域号牌限行的拥堵区路网密度及其等级配置合理,公共交通供给略有错位与不足;对外地车辆限行的拥堵区路网供给不足,公交供给水平相对较高,但在精细尺度上存在交通供给要素的错位与替代性公共交通不足的问题;根据交通供给特征及限行政策将拥堵区划分为片区式、飞地式和节点式拥堵区,分别提出实施拥堵收费、优化路网结构、提高微循环能力、增设公交线路串点成线及引导公交出行等策略,以期为大城市交通精细化治理提供借鉴。

考虑交通需求空间不平衡影响的交通指数

为精确反映整个区域或路网的实际交通运行状况,本研究先通过实例分析验证交通需求空间不平衡对区域交通运行的不利影响,再提出“延误等价”原则,以此作为评价区域交通指数准确性的新标准;其次,利用“熵权法”构建区域交通指数模型,该模型包含了反映路段几何特征、路段交通流特征、网络拓扑特征及网络交通需求不平衡特征的因素。以上海市杨浦区为例,经验证,交通指数模型不仅能够准确反映该区域的交通运行状况,还具有较好的适用性,为相关部门的规划建设和管理政策制定提供了借鉴与参考。

齐河路/华绣路人行天桥方案研究

介绍齐河路/华绣路人行天桥工程概况,其主要特点是在道路建成后新建天桥,受紧邻居民区,学校,管线限制,修建造价高、难度大,通过Z型方案满足主要交通需求的情况下降低造价,详细阐述了设计方案,有关经验为今后同类型的工程提供借鉴参考。

城市交通拥堵组合治理政策仿真研究

为探究不同交通拥堵治理政策的作用与效果,从交通发展战略、交通需求管理、交通费用调节3个方面设计了16种政策模拟情形,通过Vensim PLE软件进行仿真模拟。结果表明,交通需求管理是治理交通拥堵最有效的方式,其次是交通发展战略和交通费用调节,该实验结果为城市交通优化提供了有益参考。未来治理城市交通拥堵时,应注重调节交通需求和供给之间的矛盾,综合运用土地规划、交通管理等手段,科学控制交通需求总量、出行方式和时空分布,以实现供需在不同阶段和层次上的相对平衡,从而确保城市交通系统的可持续发展。

甘肃省铁路网高质量发展规划研究

为推动甘肃省铁路网现代化建设和综合交通高质量发展,立足新发展格局下甘肃省铁路发展现状和形势要求,对甘肃省铁路网规划布局进行系统研究。首先,对目前甘肃省铁路网布局结构、路网规模水平、运输效率、运输能力适应性等进行研究,剖析甘肃省铁路网发展存在的瓶颈弱项;其次,基于甘肃省铁路客货运输需求,以问题破解、需求支撑、发展引领为导向,提出甘肃省铁路网发展思路、发展目标和布局方案。研究表明,甘肃省将形成“一心两廊多放射”的铁路网格局,构建“1259小时交通圈”,实现区域内部市市通高速铁路、区域对外多径路快速通达、货运体系保障有力。

混合流下非机动车道基本需求宽度的设计

为弥补在非机动车道设计方面对电动自行车考虑不足的情况,有必要对由人力/电动自行车组成的饱和混合流下非机动车道基本需求宽度进行研究。以非机动车饱和混合流为研究对象,从非机动车的物理运动宽度组成出发,通过构建多重线性回归模型分析了非机动车物理运动宽度的影响因素,对分类自变量进行组合筛选;建立了不同组合类型下的非机动车速度与运行摆幅、路侧安全净距线性模型,得到性别为女性、年龄为老年和车型为电动自行车为最不利组合的结论;根据非机动车道的85%位运营速度确定最不利组合下的非机动车物理运动宽度,进而确定非机动车道基本需求宽度;针对非机动车道宽度合理性验证的准确性问题,从稳定性角度提出了运用速度熵来验证基本需求宽度合理性的方法,并以多条非机动车道路段为例进行了实测验证。研究结果表明:在隔离栏和划线下,非机动车单车道基本需求宽度分别为1.65、1.50 m;在绿化带、隔离栏和划线下,非机动车两车道基本需求宽度分别为2.90、2.80、2.65 m。在同一车道数和隔离方式下,车道宽度越宽,交通流速度熵越高;随着非机动车道宽度增加,以基本需求宽度为拐点,非机动车道的交通流速度熵变化幅度增大,稳定性更差。

考虑群体行为异质性的深港跨界口岸交通需求模型

口岸跨界交通是推动对外交流合作、经贸往来的重要支撑,精细化的跨界口岸交通需求分析和预测有助于提升口岸规划和治理水平、完善口岸基础设施服务质量。以深圳和香港地区之间的跨界客流为例,针对多元跨界群体在政策敏感性、目的地选择偏好、口岸选择偏好等方面的异质性,提出总量预测、客流分布、口岸选择“三阶段”跨界口岸交通需求模型框架。在方法上,以引力模型和离散选择模型为基础,充分考虑各类基础数据的现实局限性进行合理建模,使其兼具方法论行为基础和可用性。该模型框架从跨界群体出行行为异质性的角度为跨界口岸交通模型提供新视角,并为其他重大对外基础设施的交通需求建模提供参考。