基于互联网出行数据的停车设施选址规划方法

于晓飞; 刘兵; 陈汐; 贾婷婷; 马晓磊

doi:10.3963/j.jssn.1674-4861.2023.03.013

基于互联网出行数据的停车设施选址规划方法

doi: 10.3963/j.jssn.1674-4861.2023.03.013

于晓飞^1,,
刘兵¹,
陈汐²,
贾婷婷³,
马晓磊^{1, 4, ,}

1.
北京航空航天大学交通科学与工程学院北京 100191
2.
北京航空航天大学计算机学院北京 100191
3.
首程控股有限公司北京 100049
4.
教育部智能交通技术与系统重点实验室北京 100191

基金项目:

国家重点研发计划项目 2021YFB1600100

详细信息

作者简介:
于晓飞（1996—），硕士研究生. 研究方向：停车设施选址. E-mail: xiaofei_66@buaa.edu.cn

通讯作者:
马晓磊（1985—），博士，教授. 研究方向：交通信息工程及控制. E-mail: xiaolei@buaa.edu.cn

中图分类号: U121
计量
- 文章访问数: 525
- HTML全文浏览量: 217
- PDF下载量: 29
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-20
- 网络出版日期: 2023-09-16

A Method for Planning of Parking-facility Locations Using Internet Mobility Data

YU Xiaofei^1
,,
LIU Bing¹,
CHEN Xi²,
JIA Tingting³,
MA Xiaolei^{1, 4
, ,}

1.
School of Transportation Science and Engineering, Beihang University, Beijing 100191, China
2.
School of Computer Science and Engineering, Beihang University, Beijing 100191, China
3.
Shoucheng Holdings, Beijing 100049, China
4.
Key Laboratory of Intelligent Transportation Technology and System, Ministry of Education, Beijing 100191, China

摘要

摘要: 为解决不确定需求下的停车设施选址问题，提出了基于互联网出行数据的停车设施选址规划方法。该方法基于居民通勤数据估计停车需求、识别备选停车设施点，并以停车设施的建设维护成本、停车设施到停车需求点的步行距离最小化为目标，构建不确定需求下的停车设施选址优化模型。为验证模型的可行性，基于北京市2021年9月—11月的居民通勤数据，针对海淀区中关村附近区域，构建并求解模型，并对建设维护总成本变化与停车需求不确定性之间的关系进行研究。研究结果表明：停车设施点的最优配置数量及其车位规模会随着停车需求被满足的置信水平（即实际停车需求小于或等于停车设施容量的概率）的提高而增加，且当置信水平达到0.9时，建设维护总成本变化显著提高，此时停车设施点的数量为30个，停车位总数为28 862个。此外，建设维护总成本对停车需求不确定性水平较敏感，会随着停车需求不确定性的提升而增大，在停车需求不确定性水平分别为0.4，0.5，0.6时，停车设施建设和维护的相对总成本变化率分别为1.25，1.75，2.25，而在同一置信水平下，停车需求不确定性越高，相对总成本变化率越大，相对总成本对需求不确定性也较敏感。本研究对停车设施选址规划者，通过掌控设施点的停车容量与需求波动的情况，来有效地控制系统总成本，保证选址方案的鲁棒性。
- 城市交通 /
- 停车设施选址 /
- 不确定性停车需求 /
- 混合整数规划 /
- 互联网出行数据
Abstract: To address the issue of parking facility location under uncertain demand, a method for planning parking facility locations based on Internet mobility data is proposed. This method estimates parking demand and identifies alternative parking facility locations based on residents' commuting data. An optimization model for parking facility location under uncertain demand is developed, which has an objective function considering the construction and maintenance costs of parking facilities and the walking distance from parking facilities. To verify the feasibility of the model, a case study is conducted based on the residents' commuting data in Beijing from September to November in 2021. specifically, an optimization model is established for the area of Zhongguanchun and its surrounding areas in Haidian District and the relationship between variation of the total costs of building and maintaining the parking facilities and uncertainty of parking demand is analyzed. Study results show that the optimal number and size of parking facilities will increase as the confidence interval of satisfying the parking demand (i.e., the probability of parking demand being smaller than or equal to the capacity of parking facilities) increases. When the confidence level reaches 0.9, the variation rate of total cost is significantly increased, where the number of parking facility required is 30 with a total of 28 862 parking spots. In addition, the total system cost is sensitive to the level of uncertainty of parking demand and will increase as the level of uncertainty increases. when the level of uncertainty reaches 0.4, 0.5, and 0.6, the variation rate of relative total cost for parking facility is 1.25, 1.75, and 2.25, respectively. Under the same confidence interval, the higher the level of uncertainty of parking demand, the higher the change rate of total cost is to the level of the uncertainty of the demand. This study enables parking planners to effectively control the total system cost and to ensure the robustness of the location plan by controlling the capacity and demand fluctuations of the parking facilities.
- urban traffic /
- parking facilities location /
- mixed integer programming /
- uncertain parking demand /
- internet mobility data

HTML全文

图 1 北京市主要行政区域需求统计量

Figure 1. Demand statistics of major administrative regions in Beijing

下载: 全尺寸图片幻灯片

图 2 北京市海淀区通勤终点空间分布

Figure 2. Spatial distribution of commuters' destination in Haidian District

下载: 全尺寸图片幻灯片

图 3 研究关系及流程

Figure 3. Research relationships and processes

下载: 全尺寸图片幻灯片

图 4 备选停车点与原有设施点分布对比

Figure 4. Comparison of distribution of alternative parking spots and original facilities

下载: 全尺寸图片幻灯片

图 5 研究区域及备选点分布

Figure 5. Study area and distribution of candidate points

下载: 全尺寸图片幻灯片

图 6 停车需求确定时停车点的选址分布

Figure 6. Location distribution of parking when parking demand is certain

下载: 全尺寸图片幻灯片

图 7 原有停车点和所选停车点位置对比

Figure 7. Comparison of the original parking spot and the selected parking spot

下载: 全尺寸图片幻灯片

图 8 总成本与置信水平关系

Figure 8. Relationship between total cost and confidence level

下载: 全尺寸图片幻灯片

图 9 不确定水平不同时相对成本变化

Figure 9. Relative cost changes with different levels of uncertainty

下载: 全尺寸图片幻灯片

表 1 居民通勤数据示例

Table 1. Residential commuter data example

起点经度/（°）	起点纬度/（°）	终点经度/（°）	终点纬度/（°）	驾车人数/人
116.352 58	40.025 653	116.181 09	40.161 566	1
116.366 68	40.011 251	116.302 07	39.858 236	2
116.370 20	40.003 150	116.340 83	40.032 853	4
116.372 55	40.0103 51	116.296 20	39.896 040	1

下载: 导出CSV

表 2 停车需求点到备选停车设施点之间的距离

Table 2. Distance from parking demand point to alternative parking facility 单位: m

A	D
A	1	2	…	87	88
1	1 077.57	1 318.09	…	1 029.59	506.43
2	1 810.18	1 608.66	…	1 716.60	1 045.76
3	1 295.63	957.55	…	1 328.96	902.42
4	1 316.63	1 259.25	…	1 276.30	713.81
⋮	⋮	⋮		⋮	⋮
39	510.84	1 250.07	…	338.77	842.48
40	723.34	1 069.24	…	979.65	1 172.67

下载: 导出CSV

表 3 停车需求点的停车需求数目

Table 3. Parking demands at the parking demand point

需求点	需求量/个
1	398
2	394
3	372
⋮	⋮
86	104
87	101
88	100

下载: 导出CSV

表 4 模型假定参数

Table 4. Model assumed parameters

参数	赋值	参数	赋值
$m$	40	$f_{i}$	1000
$n$	88	$q_{i}$	80
$d_{i j}$	见表 1	$\lambda$	1
$U_{\min }$	0	$\beta_{j}$	0.5
$U_{\max }$	2000	$u_{j}$	见表 2

下载: 导出CSV

表 5 容量排名前10的停车设施点

Table 5. Top 10 parking facilities by capacity

编号	选址位置的POI	容量/个
11	知春东里社区	1512
24	万泉小学	1135
21	苏州街地铁站	1115
13	双榆树中街	1068
28	北京市海淀区妇幼保健院东南院区	1062
26	品质伊网	956
18	汇新家园	686
22	艾瑟顿国际公寓	583
12	中航广场	489
25	万泉新新家园26号	382

下载: 导出CSV

表 6 设计容量排名前10的停车设施点及停车需求量

Table 6. Top 10 parking facilities by capacity and parking demand

编号	选址位置的POI	需求量/个
11	知春东里社区	1479
24	万泉小学	1053
21	苏州街地铁站	1035
13	双榆树中街	971
28	北京市海淀区妇幼保健院东南院区	970
26	品质伊骊	945
18	汇新家园	651
22	艾瑟顿国际公寓	619
12	中航广场	492
25	万泉新新家园26号	365

下载: 导出CSV

表 7 不同置信水平下的选址方案

Table 7. Parking location at different confidence levels

$p_{j}$	$C L$	$P$	$P V$	$T$	$R C C$	$R C \%$
0.50	0.50	28	22118	3959242	1459814	58.4
0.45	0.55	28	22719	4066043	1566615	62.7
0.40	0.60	28	23344	4177392	1677964	67.1
0.35	0.65	29	24009	4320614	1821186	72.9
0.30	0.70	29	24721	4460560	1961132	78.5
0.25	0.75	29	25513	4614234	2114806	84.6
0.20	0.80	28	26414	4863813	2364385	94.6
0.15	0.85	29	27483	5064700	2565272	102.6
0.10	0.90	30	28862	5399144	2899716	116.0
0.05	0.95	30	30963	5882328	3382900	135.3
0.01	0.99	31	35052	6895008	4395580	175.9

下载: 导出CSV

参考文献(21)

[1]	李超. 城市商圈停车特性与停车选择研究[D]. 重庆: 重庆交通大学, 2014. LI C. Research on parking characteristics and parking choices in urban commercial circles[D]. Chongqing : Chongqing Jiaotong University, 2014. (in Chinese)
[2]	黄睿. 我国城市中心商业区停车问题现状及发展对策研究[D]. 西安: 西安建筑科技大学, 2003. HUNG R. Research on the current situation and development countermeasures of parking problems in my country's urban central business districts[D]. Xi'an: Xi'an University of Architecture and Technology, 2003. (in Chinese)
[3]	GARCÍA-PALOMARES J C, GUTIÉRREZ J, LATORRE M. Optimizing the location of stations in bike-sharing programs: A GIS approach[J]. Applied Geography, 2012, 35(1): 235-246.
[4]	汪光焘. 大数据时代城市交通学发展的机遇[J]. 城市交通, 2016, 14(1): 1-7. https://www.cnki.com.cn/Article/CJFDTOTAL-CSJT201601001.htm WANG G T. Opportunities for the development of urban transportation in the era of big data[J]. Urban Transportation, 2016, 14(1): 1-7. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CSJT201601001.htm
[5]	郑敏慧. 基于滴滴网约车OD数据的停车规划方法研究[D]. 北京: 北京交通大学, 2018. ZHENG M H. Research on parking planning method based on Didi. com car-hailing OD data[D]. Beijing: Beijing Jiaotong University, 2018. (in Chinese)
[6]	GUAN Y, WANG Y, YAN X, et al. A big-data-driven framework for parking demand estimation in urban central districts[J]. Journal of Advanced Transportation, 2020, (3): 1-13.
[7]	郭彦茹, 罗志雄, 王家川, 等. 数据驱动的共享单车停放区规划方法研究[J]. 交通运输系统工程与信息, 2021, 21(6): 9-16. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202106002.htm GUO Y R, LUO Z X, WANG J C, et al. Research on data-driven shared bicycle parking area planning method[J]. Transportation Systems Engineering and Information, 2021, 21(6): 9-16. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202106002.htm
[8]	KIM K, KOSHIZUKA N. Data-driven parking decisions: proposal of parking availability prediction model[C]. 16^th International IEEE Conference, Charlotte, USA: IEEE, 2019.
[9]	LI M, GAO S, LIANG Y, et al. A data-driven approach to understanding and predicting the spatiotemporal availability of street parking[C]. 27^th ACM SIGSPATIAL International Conference, Chicago, USA: Association for Computing Machinery, 2019.
[10]	FIEZ T, RATLIFF L J, DOWLING C, et al. Data driven spatio-temporal modeling of parking demand[C]. 2018 Annual American Control Conference(ACC), Milwaukee, USA: IEEE, 2018.
[11]	SANDOVAL R, VAN GEFFEN C, WILBUR M, et al. Data driven methods for effective micromobility parking[J]. Transportation Research Interdisciplinary Perspectives, 2021 (10): 100368.
[12]	陈峻, 王炜, 胡克定. 城市社会停车场选址规划模型研究[J]. 公路交通科技, 2000(1): 61-64. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK200001015.htm CHEN J, WANG W, HU K. Research on the planning model of urban social parking lot site selection[J]. Highway Traffic Science and Technology, 2000(1): 61-64. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK200001015.htm
[13]	HSU Y T, YAN S, HUANG P. The depot and charging facility location problem for electrifying urban bus services[J]. Transportation Research Part D: Transport and Environment, 2021(100): 103053.
[14]	杨宇. 城市共享新能源汽车选址-分配研究[D]. 北京: 中国矿业大学, 2019. YANG YU. Urban shared new energy vehicle site selection-allocation research[D]. Beijing: China University of Mining and Technology, 2019. (in Chinese)
[15]	邹志云. 社会公共停车场选址方法研究[J]. 武汉城市建设学院学报, 1996(4): 70-72. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCJ604.015.htm ZOU Z Y. Research on the method of site selection of social public parking lot[J]. Journal of Wuhan Urban Construction Institute, 1996(4): 70-72. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-WHCJ604.015.htm
[16]	SAIF A, DELAGE E. Data-driven distributionally robust capacitated facility location problem[J]. European Journal of Operational Research, 2021, 291(3): 995-1007.
[17]	HAMERLY G, ELKAN C. Learning the k in k-means[C]. 17th Annual Conference on Neural Information Processing Systems(NIPS 2003), Vancouver, Canada: Biologische Kybernetik, 2004.
[18]	GABREL V, LACROIX M, MURAT C, et al. Robust location transportation problems under uncertain demands[J]. Discrete Applied Mathematics, 2014(164): 100-111.
[19]	NG M, WALLER S T. Reliable evacuation planning via demand inflation and supply deflation[J]. Transportation Research Part E: Logistics and Transportation Review, 2010, 46 (6): 1086-1094.
[20]	LI Z. Optimal robust optimization approximation for chance constrained optimization problem[J]. Computers & Chemical Engineering, 2015(74): 89-99.
[21]	中华人民共和国建设部. 城市道路交通规划设计规范: GB 50220—95[S]. 北京: 人民交通出版社, 1995. Ministry of Construction of the People's Republic of China. Urban road traffic planning and design code: GB 50220-95[S]. Beijing: China Communications Press, 1995.