Dynamic train dwell time forecasting:a hybrid approach to address the influence of passenger flow fluctuations

Train timetables and operations are defined by the train running time in sections,dwell time at stations,and headways between trains.Accurate estimation of these factors is essential to decision-making for train delay reduction,train dispatching,and station capacity estimation.In the present study,we aim to propose a train dwell time model based on an averaging mechanism and dynamic updating to address the challenges in the train dwell time prediction problem(e.g.,dynamics over time,heavy-tailed distribution of data,and spatiotemporal relationships of factors)for real-time train dispatching.The averaging mechanism in the present study is based on multiple state-of-the-art base predictors,enabling the proposed model to integrate the advantages of the base predictors in addressing the challenges in terms of data attributes and data distributions.Then,considering the influence of passenger flow on train dwell time,we use a dynamic updating method based on exponential smoothing to improve the performance of the proposed method by considering the real-time passenger amount fluctuations(e.g.,passenger soars in peak hours or passenger plunges during regular periods).We conduct experiments with the train operation data and passenger flow data from the Chinese high-speed railway line.The results show that due to the advantages over the base predictors,the averaging mechanism can more accurately predict the dwell time at stations than its counterparts for different prediction horizons regarding predictive errors and variances.Further,the experimental results show that dynamic smoothing can significantly improve the accuracy of the proposed model during passenger amount changes,i.e.,15.4%and 15.5%corresponding to the mean absolute error and root mean square error,respectively.Based on the proposed predictor,a feature importance analysis shows that the planned dwell time and arrival delay are the two most important factors to dwell time.However,planned time has positive influences,whereas arrival delay has negative influences.

Exploring the Evolution of Passenger Flow and Travel Time Reliability with the Expanding Process of Metro System Using Smartcard Data

Metro system has experienced the global rapid rise over the past decades. However,few studies have paid attention to the evolution in system usage with the network expanding. The paper's main objectives are to analyze passenger flow characteristics and evaluate travel time reliability for the Nanjing Metro network by visualizing the smart card data of April 2014,April 2015 and April 2016. We performed visualization techniques and comparative analyses to examine the changes in system usage between before and after the system expansion. Specifically,workdays,holidays and weekends were specially segmented for analysis.Results showed that workdays had obvious morning and evening peak hours due to daily commuting,while no obvious peak hours existed in weekends and holidays and the daily traffic was evenly distributed. Besides,some metro stations had a serious directional imbalance,especially during the morning and evening peak hours of workdays. Serious unreliability occurred in morning peaks on workdays and the reliability of new lines was relatively low,meanwhile,new stations had negative effects on exiting stations in terms of reliability. Monitoring the evolution of system usage over years enables the identification of system performance and can serve as an input for improving the metro system quality.

Time-varying confidence interval forecasting of travel time for urban arterials using ARIMA-GARCH model

To improve the forecasting reliability of travel time, the time-varying confidence interval of travel time on arterials is forecasted using an autoregressive integrated moving average and generalized autoregressive conditional heteroskedasticity （ARIMA-GARCH） model. In which, the ARIMA model is used as the mean equation of the GARCH model to model the travel time levels and the GARCH model is used to model the conditional variances of travel time. The proposed method is validated and evaluated using actual traffic flow data collected from the traffic monitoring system of Kunshan city. The evaluation results show that, compared with the conventional ARIMA model, the proposed model cannot significantly improve the forecasting performance of travel time levels but has advantage in travel time volatility forecasting. The proposed model can well capture the travel time heteroskedasticity and forecast the time-varying confidence intervals of travel time which can better reflect the volatility of observed travel times than the fixed confidence interval provided by the ARIMA model.

Travel time prediction with viscoelastic traffic model

Travel time through a ring road with a total length of 80 km has been predicted by a viscoelastic traffic model(VEM), which is developed in analogous to the non-Newtonian fluid flow. The VEM expresses a traffic pressure for the unfree flow case by space headway, ensuring that the pressure can be determined by the assumption that the relevant second critical sound speed is exactly equal to the disturbance propagation speed determined by the free flow speed and the braking distance measured by the average vehicular length. The VEM assumes that the sound speed for the free flow case depends on the traffic density in some specific aspects, which ensures that it is exactly identical to the free flow speed on an empty road. To make a comparison, the open Navier-Stokes type model developed by Zhang(ZHANG, H. M. Driver memory, traffic viscosity and a viscous vehicular traffic flow model. Transp. Res. Part B, 37, 27–41(2003)) is adopted to predict the travel time through the ring road for providing the counterpart results.When the traffic free flow speed is 80 km/h, the braking distance is supposed to be 45 m,with the jam density uniquely determined by the average length of vehicles l ≈ 5.8 m. To avoid possible singular points in travel time prediction, a distinguishing period for time averaging is pre-assigned to be 7.5 minutes. It is found that the travel time increases monotonically with the initial traffic density on the ring road. Without ramp effects, for the ring road with the initial density less than the second critical density, the travel time can be simply predicted by using the equilibrium speed. However, this simpler approach is unavailable for scenarios over the second critical.

Stochastic network equilibrium model with reliable travel time confidence level

In order to ensure on-time arrival when travelersmake their trips, the stochastic network assignment modelunder uncertainty of travel time is investigated. First, basedon travelers＇ route choice behavior, the reliable travel timeconfidence level （RTTCL）, which is the probability that a triparrives within the shortest average travel time plus theacceptable travel time difference, is defined. Then, areliability-based user equilibrium （RUE） model, whichhypothesizes that for each OD pair no traveler can improvehis/her RTTCL by unilaterally changing routes, is built.Since the traditional traffic assignment algorithms are notfeasible to solve the RUE model, a quasi method of successiveaverage （QMSA） is developed. Using Nguyen-Dupuis andSioux Falls networks, the model and the algorithm are tested.The results show that the QMSA algorithm can rapidlyconverge to a high accuracy for solving the proposed RUEmodel, and the RUE model can provide a good response totravelers＇ behavior in the stochastic network.

基于乘客OD间路径旅行时间的城市轨道交通客流分布计算模型的适用性研究

[目的]针对目前城市轨道交通(以下简称“城轨”)线网客流分布计算模型的客流计算结果与实际客流存在偏差的现象,需基于OD间路径的实际旅行时间,对基于多路径概率分配的客流分布计算模型的适用性展开研究。[方法]基于乘客OD间路径的实际旅行时间,分析揭示了现有城轨客流分布计算模型存在的主要问题;融合AFC(自动售检票)系统和ATS(列车自动监控)系统两类数据,构建并标定了基于乘客OD间路径旅行时间的城轨客流分布计算模型;对目前国内城轨系统广泛采用的基于多路径概率分配的城轨客流分布计算模型的适用性进行了分析与评价。[结果及结论]现有城轨客流分布计算模型在路径选择集和路径选择比例上存在主要问题。通过基于多路径概率分配的城轨客流分布计算模型获取的路径分配比例,得到的旅行时间分布模拟结果均为单峰,无法重现从AFC票卡提取的实际旅行时间分布的多峰情况。当城轨线网较为简单时,基于多路径概率分配的城轨客流分布计算模型基本适用;当线网规模不断增加,线网结构进一步复杂,列车运行方式的多样性、乘客出行行为的差异性等不断加大的条件下,该模型对于路径阻抗差异小的OD可能适用,而对于路径阻抗差异大的OD不适用。

基于“互联互通”的嘉兴至枫南市域铁路列车开行方案研究

嘉兴至枫南市域铁路是浙江省嘉兴市第一条市域铁路,是长三角地区多层次轨道交通网络中重要线路之一,与嘉善至西塘市域铁路互联互通。“互联互通”条件下市域铁路网络跨线运营是未来的发展趋势,列车开行方案设计是制定市域铁路运输组织方案的前提,做好“互联互通”条件下列车开行方案的制定是运营期市域铁路运营管理的一项主要工作,也是市域铁路规划设计阶段需要重点考虑的问题。在研究嘉兴至枫南市域铁路概况的基础上,对其进行数学建模。在分析市域铁路不同列车种类的基础上,以所有乘客总体出行时间效益最大化为优化目标,应用数学规划、多目标优化的方法构建了一套“互联互通”条件下列车开行方案优化模型,包括市域铁路直达列车数量计算模型、大站快车停站选择模型和大站快车、站站停列车数量计算模型。在研究嘉兴至枫南市域铁路线路互联互通的基础上,依据初期早高峰时段客流预测结果,计算得到初期早高峰时段嘉兴南站—南枫线段采用快慢车混跑方式,大站快车停车站为科技城站、嘉善站,开行直达列车1对/h,大站快车3对/h,站站停列车5对/h;嘉兴南站—示范区线段采用快慢车混跑方式,大站快车停车站为科技城站、嘉善站、西塘站,开行大站快车2对/h,站站停列车6对/h,进而确定嘉兴至枫南市域铁路列车开行方案。

考虑乘客旅行时间价值的市域轨道交通列车开行方案

[目的]鉴于市域铁路的功能定位,以及当前经济社会发展下乘客对出行快捷性、舒适性和经济性需求不一致的特性,需对考虑乘客旅行时间价值的市域铁路列车开行方案进行研究。[方法]构建了考虑乘客旅行时间价值的列车开行方案模型。该模型以乘客出行成本和列车开行成本为目标函数,以列车定员、站间客流及列车开行数量等为主要约束条件,同时采用帕累托模型对不同乘客的时间价值和不同编组列车的开行成本进行标定。以上海市域轨道交通机场联络线为研究背景,考虑了4节与8节两种列车编组形式,对虹桥站至上海东站站单方向高峰小时的列车开行方案进行了计算分析及评价。[结果及结论]考虑乘客旅行时间价值的列车开行方案能最大限度地减少乘客出行成本,更好地满足不同乘客的出行时间需求;增加乘客旅行时间价值较低的乘客旅行时间,缩短乘客旅行时间价值较高的乘客旅行时间,能更好地发挥列车开行方案的经济效益。

基于TIMES模型的客运交通低碳化研究——以北京市为例

为研究低碳城市环境下居民的客运交通出行,以综合能源优化模型——TIMES(The Integrated MARKALEFOM System)模型为分析工具,构建客运交通模型。该模型考虑了出行成本、出行选择行为、碳减排目标等的影响,同时以北京市为例,设计基准情景和3个参考情景并对不同情景进行分析和讨论。结果显示:当减少出行时间投资成本非常高时,居民很大程度上通过小汽车来满足居民出行需求。在CO2排放限制情景下,小汽车出行需求不断下降,道路公交和轨道交通出行需求稳步上升。基于上述结果得出北京市客运交通低碳化发展的对策和建议:即调控出行需求结构;优化交通出行结构;调整交通能源结构;完善交通治理结构。

基于Prophet的民航商务旅客出行量预测研究

随着民航业竞争日益加剧,民航市场需求的细分和预测对于民航业的发展具有重要意义。而商务旅客作为民航客源重要组成部分,民航商务旅客出行量的准确预测,为民航业的科学规划、运营管理和收益管理等提供重要的决策依据。为探索一种准确率高、可解释性强的预测算法,对民航商务旅客出行量数据进行了可视化和分析,结合数据特点提出了基于Prophet模型的民航商务旅客出行量预测方法,并通过真实的民航商务旅客出行量数据进行实验和分析。实验结果表明,基于Prophet的模型与同类的ARIMA模型和LSTM模型相比,具有更高的预测精准度,同时具有更强的可解释性,证明了方法的有效性。

城市机场枢纽可达性及均衡水平分析与评估

2021年中共中央、国务院印发了《国家综合立体交通网规划纲要》,纲要对推进综合交通发展、优化交通布局提出明确要求,其中更是对2035年国家综合立体交通网提出九大指标,其中便包含了中心城区至综合客运枢纽半小时可达率的要求。文章通过对上海市机场枢纽的可达性及均衡水平进行分析,结合加权平均旅行时间与可达性差距指数(MA G)找出交通网络中的不足,旨在为交通运输相关部门进行交通规划与资源分配时提供决策参考。

基于等间隔运行模式的群组电梯系统优化调度方法

针对群组电梯系统运行调度优化问题,本文采用多目标优化模型,基于电梯群组等间隔运行模式的操作规则,建立一类以乘客平均候梯时间最短为主要目标的群组优化策略.通过分析群组电梯系统运行中乘客候梯时间、服务时间、轿厢拥挤度和电梯能耗等指标,建立电梯系统运行的动态指标评价模型,考虑电梯客流的随机性因素,提出乘客候梯等间隔派梯规则和算法,实现了电梯系统多目标优化的动态调度方法.实验结果表明,对比传统的最短距离调度算法,本文方法可以降低乘客平均候梯时间13.1%,提高群组电梯系统工作性能.

城市轨道交通车站高峰时段与高峰客流预测模型

现有轨道交通车站高峰客流预测方法简化了车站高峰形成过程,基于默认假设,即车站高峰小时与所属线路高峰小时一致进行预测,忽略了车站与线路间存在的高峰偏差现象,造成部分车站高峰客流量被低估,导致车站能力设计不足,站台拥挤风险增加。从车站高峰形成机理出发,基于用地发生率模型,考虑不同目的出行行为的差异化,对客流属性进行划分,引入不同目的的出行时间概率分布函数,建立站点尺度的高峰小时与高峰客流预测模型框架。该模型真实反映了车站高峰与高峰偏差现象形成的这一复杂过程,可解释性强、符合实际,且能适用于建成环境、车站特征和轨道交通网络服务等变化情形下的车站高峰客流预测。验证结果显示:1)提出模型较传统模型提升了43%~47%的车站预测精度(高峰客流相应的MAPE值下降了5.7%~6.38%,高峰时间相应的APE值下降了23~50 min),具有更广泛的适用性和更稳定、更准确的预测结果,能为车站设计和运营方案制定提供更可靠的决策依据;2)各类出行目的的峰值和峰尺度存在差异,按不同比例叠加后,会产生不同的叠加曲线。揭示了车站高峰客流形成机理为不同用地产生的不同出行目的客流时间分布叠加曲线的高峰。

中欧班列对中国与哈萨克斯坦可达性的影响研究

哈萨克斯坦是中国重要的贸易伙伴,在中欧班列开通后两国双边贸易额不断攀升,对两国经济产生了积极的影响。以中欧班列国内沿线城市与哈萨克斯坦各州域为研究对象,构建经济潜力与加权平均旅行时间模型,量化中欧班列国内沿线城市与哈萨克斯坦州域间的可达性。结果表明中欧班列使中哈加权平均旅行时间减少90.6%,经济潜能平均增大15.08倍,促进了中哈两国的可达性。中欧班列对中国与哈萨克斯坦的可达性改善作用存在差异性,对国内沿线城市可达性促进作用强于哈萨克斯坦各州域,国内地区中加权平均旅行时间改善程度呈内陆向沿海、北部向南部递减的特点,西北地区的经济潜力得到明显改善;哈萨克斯坦州域改善程度呈由东向西递减的地域特征。

城市轨道交通虚拟编组列车优化运行方案研究

虚拟编组技术通过车-车无线通信实现车辆“虚拟连接”。虚拟编组列车车辆间无机械车钩连挂装置,在运行过程中可以进行动态连挂和解编操作,能够基于客流变化实现灵活的运输模式。本文以缩短乘客旅行时间和提高列车运输效率为目标,提出虚拟编组列车运行方案的优化方法,并基于实际城市轨道交通线路早高峰客流OD(original-destination)数据给出优化设计结果。虚拟编组优化运行方案与现行方案的仿真结果表明,虚拟编组优化方案在保证运输效率的同时,可以有效缩短乘客旅行时间,提升轨道交通客运服务质量。

出行方式转移行为特征分析——以北京市为例

对规划与政策可控变量组合情景下的转移行为特征实证分析在现有出行方式转移研究中较为少见。以北京市为例,对3 351名出行者进行出行方式转移意向调查(SP调查),识别出4类转移意愿群体。首先分析出行时间比和停车费用两个变量对不同群体的影响。然后,对比不同组合情景下出行方式转移率的变化,以反映公共交通出行效率改善和小汽车使用成本提高对不同群体出行方式转移意愿的影响程度。结果表明:降低出行时间比对于提高公共交通乘客依赖度和减少乘客流失效果较好,但是很难吸引对小汽车高度依赖的出行者;提高停车费用对于引导摇摆群体从小汽车出行向公共交通转移效果显著。两个变量所产生的出行方式转移率受到现状基准值的影响,在制定政策时需统筹考虑两者的互动关系。最后,提出应结合出行调查数据制定分区域、分群体、分目的的公共交通吸引力提升策略,探索精细化、可实施、重统筹的公共交通发展及交通治理路径。

Short-term inbound rail transit passenger flow prediction based on BILSTM model and influence factor analysis

Accurate and real-time passenger flow prediction of rail transit is an important part of intelligent transportation systems(ITS).According to previous studies,it is found that the prediction effect of a single model is not good for datasets with large changes in passenger flow characteristics and the deep learning model with added influencing factors has better prediction accuracy.In order to provide persuasive passenger flow forecast data for ITS,a deep learning model considering the influencing factors is proposed in this paper.In view of the lack of objective analysis on the selection of influencing factors by predecessors,this paper uses analytic hierarchy processes(AHP)and one-way ANOVA analysis to scientifically select the factor of time characteristics,which classifies and gives weight to the hourly passenger flow through Duncan test.Then,combining the time weight,BILSTM based model considering the hourly travel characteristics factors is proposed.The model performance is verified through the inbound passenger flow of Ningbo rail transit.The proposed model is compared with many current mainstream deep learning algorithms,the effectiveness of the BILSTM model considering influencing factors is validated.Through comparison and analysis with various evaluation indicators and other deep learning models,the results show that the R2 score of the BILSTM model considering influencing factors reaches 0.968,and the MAE value of the BILSTM model without adding influencing factors decreases by 45.61%.

轨道交通换乘常规公交平均候车时间模型

乘客平均候车时间建模在公交网络协调优化研究、公共交通效益分析等诸多研究领域起着至关重要的作用.本文首先将轨道换乘常规公交的客流分为固定客流和随机客流,并进行客流到站时间分布曲线拟合,结果表明固定客流到站时间的对数正态分布拟合效果最好,而随机客流到站时间的伽马分布拟合效果最好;在此研究的基础上,建立了基于客流分类的换乘客流晚高峰平均候车时间模型;最后,对北京市13号线龙泽站519路公交线路进行了模型应用,以检验模型的准确性.检验结果表明:模型能够准确地估计晚高峰换乘乘客的平均候车时间,相对误差在2.05%以内.

北京市居民出行时间成本研究

采用收入法,考虑出行目的、出行方式等因素,给出居民出行时间成本计算的方法与步骤,将居民出行时间价值货币化。以北京市2000年和2005年为对象年,估算了分目的、分方式出行对应的单位时间价值,并根据历年交通调查的数据,获取了当年北京市全社会小汽车、公共交通(包括轨道交通)、出租汽车的平均出行时间和出行量,计算得到北京市全社会当年居民出行的时间成本。

高速铁路建设对我国省际可达性空间格局的影响

以省会城市为网络中的节点,采用加权平均旅行时间指标对我国"四纵四横"高速铁路网及长三角、珠三角和环渤海地区城际客运系统建成前后省际可达性及演变态势进行分析。研究表明,高速铁路建设使东中西地带内、地带间及省区的总体可达性均获得了大幅度提升,可达性中心区的范围沿骨干客运专线向华南、西南和西北地区拓展,圈层状空间格局依然很突出,两极分化趋势在加剧,高速铁路网建设对各地区的空间经济效应还存在很大差异。经过对高速铁路建成前后各省区的地带内、地带间及总体可达性空间格局的对比分析,从客观上论证了高速铁路建设的必要性及加强省际经济联系的重要性。