基于遗传算法的高峰时段车站协同限流方法

申梦君; 董宁宁; 李铁柱; 郭竞文; 刘慧

doi:10.3963/j.jssn.1674-4861.2024.01.015

基于遗传算法的高峰时段车站协同限流方法

doi: 10.3963/j.jssn.1674-4861.2024.01.015

1.
东南大学交通学院南京 211189
2.
南京地铁运营有限责任公司南京 211135
3.
南京铁道职业技术学院运输管理学院南京 210031

基金项目:

国家重点研发计划项目 2021YFE0112700

江苏轨道交通产业发展协同创新基地开放基金项目 N0.GCXC2104

详细信息

作者简介:
申梦君（2000—），硕士研究生. 研究方向: 城市轨道交通客流分配. E-mail: 2392198543@qq.com

通讯作者:
李铁柱（1971—），博士，教授. 研究方向：城市轨道交通运营. E-mail: litiezhu@seu.edu.cn

中图分类号: U293.5+4
计量
- 文章访问数: 27
- HTML全文浏览量: 14
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2023-03-29
- 网络出版日期: 2024-05-31

A Method for Coordinated Passenger Flow Control at Stations During Peak Period Based on Genetic Algorithms

1.
School of Transportation, Southeast University, Nanjing 211189, China
2.
Nanjing Metro Operation Co., Ltd, Nanjing 211135, China
3.
School of Transportation and Management, Nanjing Vocational Institute of Railway Technology, Nanjing 210031, China

摘要

摘要: 车站限流是缓解城市轨道交通高峰客流拥挤的有效应对措施。然而，目前实际应用的限流措施缺乏对同线路相邻车站的协同配合的考虑，限流效果有待进一步提升。综合考虑乘客、列车、车站三者的交互关系，依据列车在车站的发车时间间隔，对高峰时段的列车时刻表进行时间离散化，将离散化的时段作为基本研究时段，提取对应的车站乘客到达量。从供需双方的角度出发，以乘客总延误时间最小化和旅客周转量最大化为优化目标，在考虑列车运输能力、客流控制强度、车站服务水平的同时，引入列车剩余运输能力作为约束条件，平衡不同车站的客流需求，构建车站协同限流优化模型。针对多目标函数求解的复杂性，设计1种嵌入式遗传算法对模型进行求解，平衡多目标函数之间最优解的冲突。以南京地铁三号线高峰时段为例，与不采取协同限流的情景（先到先服务）进行对比分析。结果表明：在乘客总周转量提升1%的情况下，乘客延误人数下降了2.3%，乘客总延误时间降低了4.3%，拥挤车站的延误人数显著降低，延误人数的时空分布更加平衡。为了验证算法的有效性和模型的稳定性，将遗传算法与Gurobi求解器进行算法对比，并对关键参数列车满载率进行灵敏度分析，提出的遗传算法更能兼顾双优化目标，有利于缓解高峰时段大客流延误。
- 城市轨道交通 /
- 高峰客流 /
- 协同限流 /
- 遗传算法 /
- 运输能力
Abstract: Passenger flow control at urban rail transit stations is an effective strategy for alleviating congestion during peak periods. However, existing measures often overlook cooperative relations among adjacent stations along the same line, indicating the need for further improvements to enhance its efficacy. In this paper, the interaction among passengers, trains, and stations is considered comprehensively. Train schedules are discretized during peak hours based on departure intervals at stations. These discrete time periods are utilized as the basis for our research and corresponding passenger arrival data are extracted accordingly. Taking into account both supply and demand considerations, optimization objectives focus on two primary aims of minimizing aggregate passenger delay time and maximizing passenger turnover volume. Considering the train transportation capacity, passenger flow control intensity, and station service level, the remaining train transportation capacity is introduced as a constraint to balance the passenger flow demand of different stations, and an optimization model station for coordinated station flow control is constructed. Given the complexity in solving multi-objective functions, an embedded genetic algorithm is proposed to address conflicts among optimal solutions. Using Line 3 of the Nanjing Metro as a case study, a comparative analysis is conducted with the scenario without coordinated flow control (first-come-first-served) during peak hours. The results show that a 1% increase in total passenger turnover results in a 2.3% decrease in the number of passenger delays, a 4.3% decrease in total passenger delay time, and significant alleviations of delays at congested sta-tions, leading to a more balanced spatial and temporal distribution of delays. To verify the algorithm's effectiveness and the model's stability, the genetic algorithm is compared with the Gurobi solver, and the sensitivity of a key parameter, the train load factor, is analyzed. The proposed genetic algorithm demonstrates better performance in addressing the dual optimization objective, thus aiding in the mitigation of significant passenger delays during peak hours.
- urban rail transit /
- peak passenger flow /
- coordinated passenger flow control /
- genetic algorithm /
- transportation capacity

HTML全文

图 1 高峰时段车站延误人数示意图

Figure 1. Diagram of the number of delayed passengers at stations during peak hours

下载: 全尺寸图片幻灯片

图 2 不同站台乘客到达时间

Figure 2. Arrival time of passengers on different platforms

下载: 全尺寸图片幻灯片

图 3 染色体编码

Figure 3. chromosome coding

下载: 全尺寸图片幻灯片

图 4 染色体交换形式

Figure 4. Chromosome exchange form

下载: 全尺寸图片幻灯片

图 5 算法流程图

Figure 5. Algorithm flow chart

下载: 全尺寸图片幻灯片

图 6 优化前后延误人数时空分布

Figure 6. Spatial and temporal distribution of delayed people before and after optimization

下载: 全尺寸图片幻灯片

图 7 协同与非协同方案上车人数时空对比

Figure 7. A spatial-temporal comparison of the number of passengers in collaborative and non-collaborative schemes

下载: 全尺寸图片幻灯片

图 8 列车运输能力平均利用率

Figure 8. Average utilization rate of train transport capacity

下载: 全尺寸图片幻灯片

表 1 高峰时段部分车站到达客流量

Table 1. Inbound passenger flow at some stations during peak hours 单位: 人/min

站点	时刻
站点	07：20：00	07：23：00	07：26：00	07：28：15	07：59：45	08：02：00	08：18：00	08：20：00
林场	36	55	61	63	46	66	47	34
星火路		31	35	72	50	32	11	16
东大成贤学院			148	105	75	76	57	45
泰冯路				206	200	195	209	182
天润城					361	308	200	182
柳洲东路					463	462	341	386
⋮					⋮	⋮	⋮	⋮
大行宫					544	542	531	536
⋮					⋮	⋮	⋮	⋮
南京南站							236	263
宏运大道							21	17
胜太西路							62	56

下载: 导出CSV

表 2 模型相关参数

Table 2. Parameters related to the model

参数	数值	说明
列车最大满载率α	0.9	列车实际载客人数与定员的比值
列车定员C/人	1 860	采用6编组A型车
最大限流率δ/%	50	车站最大的限流率
客流放大系数θ	1.2	部分拥挤车站客流量放大

下载: 导出CSV

表 3 非协同限流与协同限流优化方案对比

Table 3. Comparison of non-collaborative and collaborative optimization schemes

指标	非协同限流	协同限流	优化量	优化幅度/%
乘客延误人数	8 329	8 140	189	+2.3
乘客延误总时间/min	18 790	17 970	820	+4.3
乘客周转量/（人?km）	5.365 4×10⁵	5.404 8×10⁵	3 940	+1

下载: 导出CSV

表 4 算法结果对比

Table 4. Comparison of algorithm results

算法	乘客延误总时间/min	乘客总周转量/（人?km）
Matlab+遗传算法	17 970	5.404 8×10⁵
Python+Gurobi	17 927	5.365 3×10⁵
未采取协同限流	18 790	5.365 4×10⁵

下载: 导出CSV

表 5 满载率对总延误时间的灵敏度分析

Table 5. Sensitivity analysis of load rate to total delay time

满载率	乘客总延误时间/min
满载率	非协同限流	协同限流	优化幅度/%
1	4 359	16 962	-289.1
0.9	18 790	17 970	+4.3
0.8	90 481	60 010	+33.7
0.7	167 494	104 718	+37.5

下载: 导出CSV

表 6 满载率对总周转量的灵敏度分析

Table 6. Sensitivity analysis of load rate to total turnover

满载率	乘客总周转量/（人?km）
满载率	非协同限流	协同限流	优化幅度/%
1	5.420 5×10⁵	5.369 7×10⁵	-1
0.9	5.365 4×10⁵	5.404 8×10⁵	+1
0.8	5.124 5×10⁵	5.222 1×10⁵	+2
0.7	4.781 2×10⁵	5.056 4×10⁵	+6

下载: 导出CSV

参考文献(26)

[1]	刘莲花, 蒋亮. 城市轨道交通网络客流控制方法研究[J]. 铁道运输与经济, 2011, 33(5): 51-55 https://www.cnki.com.cn/Article/CJFDTOTAL-TDYS201105022.htm LIU L H, JIANG L. Research on passenger flow control method of urban rail transit network[J]. Railway Transportation and Economy, 2011, 33(5): 51-55. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TDYS201105022.htm
[2]	姚向明, 赵鹏, 乔珂, 等. 城市轨道交通线路高峰客流控制方案鲁棒优化模型[J]. 铁道学报, 2021, 43(11): 29-37. https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB202111004.htm YAO X M, ZHAO P, QIAO K, et al. Robust optimization model of designing inflow control scheme for urban rail transit line during peak hours[J]. Journal of the China Railway Society, 2021, 43(11): 29-37. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB202111004.htm
[3]	李登辉, 彭其渊, 鲁工圆, 等. 城市轨道交通高峰线路客流协同控制方法[J]. 交通运输系统工程与信息, 2019, 19(6): 141-147. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201906021.htm LI D H, PENG Q Y, LU G Y, et al. Control method for passenger inflow control with coordination on urban rail transit line in peak hours[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(6): 141-147. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201906021.htm
[4]	冯树民, 陈勇, 辛梦薇. 突发大客流下地铁协调限流优化模型[J]. 哈尔滨工业大学学报, 2019, 51(2): 179-185. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201902026.htm FENG S M, CHEN Y, XING M W. Coordination passenger flow control model for metro under sudden large passenger flow[J]. Journal of Harbin Institute of Technology, 2019, 51(2): 179-185. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201902026.htm
[5]	杨静, 代盛旭, 周浪雅, 等. 城市轨道交通相邻多车站动态协同限流研究[J]. 铁道运输与经济, 2020, 42(3): 112-118. https://www.cnki.com.cn/Article/CJFDTOTAL-TDYS202003021.htm YANG J, DAI S X, ZHOU L Y, et al. A study on passenger flow control with multi-station dynamic coordination in urban transit system[J]. Railway Transport and Economy, 2020, 42(3): 112-118. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TDYS202003021.htm
[6]	YUAN F, SUN H, KANG L, et al. Passenger flow control strategies for urban rail transit networks[J]. Applied Mathematical Modelling, 2020, 82: 168-188. doi: 10.1016/j.apm.2020.01.041
[7]	JIANG Z, FAN W, LIU W, et al. Reinforcement learning approach for coordinated passenger inflow control of urban rail transit in peak hours[J]. Transportation Research Part C: Emerging Technologies, 2018, 88: 1-16.
[8]	XUE H, JIA L, GUO J. Adaptive multilevel collaborative passenger flow control in peak hours for a subway line[J]. Advances in Mathematical Physics, 2020, 2020: 1-16.
[9]	李鹏飞, 厉立. 城市轨道交通联动限流算法及实例分析[J]. 交通工程, 2022, 22(4): 33-39. https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA202204005.htm LI P F, LI L. Coordinated passenger flow limiting algorithm of urban rail transit and case analysis[J]. Journal of Transportation Engineering, 2022, 22(4): 33-39. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA202204005.htm
[10]	赵庆亮, 冯晓斌, 吴枫, 等. 基于滚动时域控制的轨道交通车站单站限流策略研究[J]. 山东科学, 2023, 36(1): 99-106. https://www.cnki.com.cn/Article/CJFDTOTAL-SDKX202301013.htm ZHAO Q L, FENG X B, WU F, et al. Single station traffic restriction strategy of rail transportation based on receding horizon control[J]. Shandong Science, 2023, 36(1): 99-106. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SDKX202301013.htm
[11]	张辉. 基于强化学习的城轨客流控制与列车跳站协同优化研究[D]. 北京: 北京交通大学, 2022. ZHANG H. Research on collaborative optimization of passenger flow control and train skip-stopping in urban rail transit based on reinforcement learning[D]. Beijing: Beijing Jiaotong University, 2022. (in Chinese)
[12]	蒋琦玮, 蔡适, 陈维亚, 等. 城市轨道交通车站客流控制决策模型[J]. 系统工程, 2017, 35(9): 94-102. https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT201709012.htm JIANG W Q, CAI S, CHEN W Y, et al. Passenger flow control decision-making model of urban rail transit station[J]. Systems Engineering. 2017, 35(9): 94-102. (in chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT201709012.htm
[13]	卢亚菡, 杨立兴, 孟凡婷, 等. 城轨线路列车时刻表与车站客流控制协同优化方法[J]. 交通运输系统工程与信息, 2021, 21(6): 195-202. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202106022.htm LU Y H, YANG L X, MENG F T, et al. Collaborative optimization of train timetable and passenger flow control strategy for urban rail transit[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 195-202. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202106022.htm
[14]	蒋琦玮, 苏建凯, 陈维亚. 考虑跨站停车的地铁客流协同控制模型[J]. 铁道科学与工程学报, 2021, 18(11): 2857-2864. https://www.cnki.com.cn/Article/CJFDTOTAL-CSTD202111008.htm JIANG Q W, SU J K, CHEN W Y. Collaborative control model of metro passenger flow considering skip-stop strategy[J]. Journal of Railway Science and Engineering, 2021, 18(11): 2857-2864. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CSTD202111008.htm
[15]	韩忠贵. 基于跨站停车的地铁高峰时段多车站协同客流控制方案研究[D]. 南昌: 华东交通大学, 2022. HAN Z G. The passenger flow control model research based on cross-station parking and station passenger flow control strategy during peak hours[D]. Nangchang: East China Jiaotong University, 2022. (in Chinese)
[16]	LU Y, YANG L, YANG K, et al. A distributional robust opti-mization method for passenger flow control strategy and train scheduling on an urban rail transit line[J]. Engineering, 2022, 12: 202-220.
[17]	JIANG Z, HSU C, ZHANG D, et al. Evaluating rail transit timetable using big passengers'data[J]. Journal of Computer and System Sciences, 2016, 82(1): 144-155.
[18]	YUAN F, SUN H, KANG L, et al. Joint optimization of train scheduling and dynamic passenger flow control strategy with headway-dependent demand[J]. Transportmetrica, 2022, 10(1): 627-651.
[19]	朱凌. 不确定环境下城市轨道交通列车交路计划与时刻表编制协同优化策略[D]. 北京: 北京交通大学, 2022. ZHU L. Collaborative optimization strategy of urban rail transit short-turning plan and train scheduling under uncertain environment[D]. Beijing: Beijing Jiaotong University, 2022. (in Chinese)
[20]	康崇仁, 杨欣, 张萍, 等. 地铁乘客限流控制与列车运行图协同优化方法研究[J]. 交通运输工程与信息学报, 2023, 21(1): 94-112. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC202301007.htm KANG C R, YANG X, ZHANG P, et al. Collaborative optimization method of passenger flow control and train timetable for metro systems[J]. Journal of Transportation Engineering and Information, 2023, 21(1): 94-112. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC202301007.htm
[21]	陈维亚, 章雍, 陈鑫, 等. 城市轨道交通大小交路开行方案与多站联合限流协同优化研究[J]. 交通运输系统工程与信息, 2019, 19(5): 177-184. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201905025.htm CHEN W Y, ZHANG Y, CHEN XIN, et al. Collaborative full-length and short-turning plan and joint multi-station control of passenger flow in urban rail transit[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(5): 177-184. (in chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201905025.htm
[22]	林立, 孟学雷, 程晓卿, 等. 考虑碳排放效果的城轨列车开行方案编制方法[J]. 交通信息与安全, 2023, 41(5): 176-184. doi: 10.3963/j.jssn.1674-4861.2023.05.018 LIN L, MENG X L, CHENG X Q, et al. A method for developing service plan of urban rail train considering carbon emissions impacts[J]. Journal of Transport Information and Safety, 2023, 41(5): 176-184. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2023.05.018
[23]	刘春宏. 基于历史数据的轨道交通网络大客流分级协同组织模型及算法分析[J]. 交通世界(上旬刊), 2019(8): 12-13. https://www.cnki.com.cn/Article/CJFDTOTAL-JTSJ201922004.htm LIU C H. Hierarchical collaborative organization model and algorithm analysis of large passenger flow in rail transit network based on historical data[J]. Transportation World(last issue), 2019(8): 12-13. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTSJ201922004.htm
[24]	赵鹏, 姚向明, 禹丹丹. 高峰时段城市轨道交通线路客流协调控制[J]. 同济大学学报(自然科学版), 2014, 42(9): 1340-1346, 1443. https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201409006.htm ZHAO P, YAO X M, YU D D. Cooperative passenger inflow control of urban mass transit in peak hours[J]. Journal of Tongji University (Natural Science), 2014, 42(9): 1340-1346, 1443. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201409006.htm
[25]	李雨恒. 高峰期地铁客流网络协调控制研究——以广州地铁为例[D]. 广州: 华南理工大学, 2021. LI Y H. Research on network coordinated control of subway passenger flow during peak period: a case study of guangzhou metro[D]. Guangzhou: South China University of Technology, 2021. (in chinese)
[26]	王久亮. 城市轨道交通车站设施设备服务水平分级与能力计算方法研究[D]. 北京: 北京交通大学, 2011. WANG J L. Research on service level classification and capacity calculation method of urban rail transit station facilities[D]. Beijing: Beijing Jiaotong University, 2011. (in Chinese)