Multimodal Public Transportation Route Planning Considering Personalized Travel Demand
-
摘要:
在多模式公交出行中,传统的路径规划方案已无法满足出行者日益增长的出行需求. 为提供基于出行者多种出行需求的个性化路径规划方案,通过IC卡刷卡数据模拟公交时刻表,建立基于模拟时刻表的多模式公交路网模型;采用动态阈值化法建立个性化出行需求评价值模型;设计深度优先搜索-遗传算法(depth first search-genetic algorithm,GA-DFS),并基于此组合算法提出初始种群产生策略和两点变异方法;最后,假设了3种不同出行需求的出行场景,将某市区的多模式公交路网数据应用于模型和求解算法中,并与使用较广的模拟退火-遗传算法(simulated annealing-genetic algorithm,GA-SA)进行对比分析. 仿真结果表明:所提出的算法与模拟退火-遗传算法相比,平均迭代次数减少了42%,寻优能力提高了50%,并且可以提供基于乘客多种出行需求的路径规划方案.
Abstract:Traditional route planning scheme cannot meet the increasing travel demand of travelers in the process of multimodal transportation. To provide personalized route planning scheme based on various travel demands of travelers, public transport timetable is simulated with the integrated circuit card data, and a multimodal transportation network modal is established based on simulated schedule. A dynamic thresholding method is used to establish the personalized travel demand evaluation value model. The depth first search-genetic algorithm (GA-DFS) is designed, and the initial population generation strategy and two-point mutation method based on this combination algorithm are proposed. Finally, three scenarios with different travel demands are assumed, the example data of a multimodal transportation network in an urban area is applied to the modal and the solution algorithm, comparing with the simulated annealing-genetic algorithm (GA-SA) which is widely used. The results show that compared with GA-SA, the proposed algorithm reduces the average number of iterations by 42%, improves the optimization ability by 50% and provides a route planning scheme based on multiple travel demands of passengers.
-
表 1 IC卡刷卡数据
Table 1. IC card data
线路编号 线路名称 交易日期时间 000382 382 路 2017-03-13 07:23:08 000382 382 路 2017-03-13 07:23:10 000382 382 路 2017-03-13 07:23:12 000382 382 路 2017-03-13 07:29:44 000382 382 路 2017-03-13 07:29:47 000382 382 路 2017-03-13 07:29:48 000382 382 路 2017-03-13 07:29:52 000382 382 路 2017-03-13 07:29:54 000382 382 路 2017-03-13 07:29:55 000382 382 路 2017-03-13 07:29:56 表 2 传统时刻表和模拟时刻表
Table 2. Traditional timetable and simulated timetable
站台号 382 路公交车到站时刻 传统时刻表 模拟时刻表 38 07:22:32 07:23:10 39 07:24:25 07:29:51 表 3 不同出行场景下的算法对比
Table 3. Comparison of algorithms under different scenarios
遗传 参数 场景一 场景二 场景三 GA-DFS GA-SA GA-DFS GA-SA GA-DFS GA-SA PC PM ATC/
元ATN/
次AI/
次ATC/
元ATN/
次AI/
次ATT/
minATN/
次AI/
次ATT/
minATN/
次AI/
次AWD/
mATC/
元AI/
次AWD/
mATC/
元AI/
次0.9 0.10 0.96 1.2 17.80 1.76 2.2 30.62 39 1.5 18.90 47 1.9 31.85 600 0.96 19.66 900 1.80 28.95 0.9 0.05 1.24 1.3 21.70 1.88 2.1 32.10 41 1.3 23.60 52 1.9 33.50 650 1.22 24.10 950 1.96 32.70 0.8 0.10 1.32 1.4 23.20 1.96 2.2 31.43 45 1.5 22.30 54 1.8 33.61 700 1.48 22.71 1000 2.04 30.24 0.7 0.10 1.60 1.4 25.60 2.16 2.1 33.95 44 1.4 24.80 64 1.8 34.46 700 1.66 24.53 1050 2.12 31.67 0.6 0.05 1.80 1.9 26.80 2.34 2.2 35.72 50 1.4 27.60 66 1.8 38.73 850 1.88 27.47 1100 2.12 34.81 表 4 相同参数、不同种群规模在场景一下的算法对比
Table 4. Comparison of algorithms with the same parameters and different population sizes under scene one
种群规模 GA-DFS GA-SA ATC/元 ATN/次 ATC/元 ATN/次 60 0.88 1.10 1.04 1.30 90 0.80 1.00 0.96 1.20 120 0.80 1.00 0.80 1.00 150 0.80 1.00 0.80 1.00 -
[1] 沈犁,张殿业,向阳,等. 城市地铁-公交复合网络抗毁性与级联失效仿真[J]. 西南交通大学学报,2018,53(1): 156-163,196. doi: 10.3969/j.issn.0258-2724.2018.01.019SHEN Li, ZHANG Dianye, XIANG Yang, et al. Simulation on survivability and cascading failure propagation of urban subway-bus compound network[J]. Journal of Southwest Jiaotong University, 2018, 53(1): 156-163,196. doi: 10.3969/j.issn.0258-2724.2018.01.019 [2] 陈海鹏,刘陪,申铉京,等. 实时环境下多目标的路径选择模型[J]. 哈尔滨工程大学学报,2017,38(8): 1285-1292.CHEN Haipeng, LIU Pei, SHEN Xuanjing, et al. Route choice model based on multi-objective in a real-time environment[J]. Journal of Harbin Engineering University, 2017, 38(8): 1285-1292. [3] 付旻. 城市多模式公共交通网络计算机模型构建技术研究[D]. 南京: 东南大学, 2018. [4] 黄明华,瞿何舟,刘晓波,等. 换乘导向的轨道交通网络发车时间优化研究[J]. 西南交通大学学报,2017,52(2): 326-333. doi: 10.3969/j.issn.0258-2724.2017.02.016HUANG Minghua, QU Hezhou, LIU Xiaobo, et al. Transfer-oriented dispatching optimization of rail transit network[J]. Journal of Southwest Jiaotong University, 2017, 52(2): 326-333. doi: 10.3969/j.issn.0258-2724.2017.02.016 [5] 张瑞兵. 基于多目标优化的城际多模式出行路径规划[D]. 哈尔滨: 哈尔滨工业大学, 2020. [6] IDRI A, OUKARFI M, BOULMAKOUL A, et al. A new time-dependent shortest path algorithm for multimodal transportation network[J]. Procedia Computer Science, 2017, 109: 692-697. doi: 10.1016/j.procs.2017.05.379 [7] DIB O, MOALIC L, MANIER M A, et al. An advanced GA-VNS combination for multicriteria route planning in public transit networks[J]. Expert Systems with Applications, 2017, 72: 67-82. doi: 10.1016/j.eswa.2016.12.009 [8] 赵婷,彭勇,程真,等. 旅客视角下基于时变的多模式交通网络出行路径[J]. 科学技术与工程,2019,19(26): 369-375. doi: 10.3969/j.issn.1671-1815.2019.26.058ZHAO Ting, PENG Yong, CHENG Zhen, et al. The travel path of multi-mode traffic network based on time-dependent from the perspective of passenger[J]. Science Technology and Engineering, 2019, 19(26): 369-375. doi: 10.3969/j.issn.1671-1815.2019.26.058 [9] 李浩楠,曹成铉,柳雨彤,等. 考虑不确定因素的多模式城市交通网络路径决策[J]. 科学技术与工程,2019,19(12): 319-324. doi: 10.3969/j.issn.1671-1815.2019.12.046LI Haonan, CAO Chengxuan, LIU Yutong, et al. Multi-modal urban transportation network route decision based on uncertainties[J]. Science Technology and Engineering, 2019, 19(12): 319-324. doi: 10.3969/j.issn.1671-1815.2019.12.046 [10] 赖元文,张杰. 基于模拟退火-自适应布谷鸟算法的城市公交调度优化研究[J]. 交通运输系统工程与信息,2021,21(1): 183-189.LAI Yuanwen, ZHANG Jie. Urban bus scheduling optimization based on simulated anneal-adaptive cuckoo search algorithm[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(1): 183-189. [11] 李衬衬,孙锋,孙猛,等. 基于深度优先搜索算法的交通流向供需失衡路径辨识[J]. 科学技术与工程,2021,21(14): 6026-6031. doi: 10.3969/j.issn.1671-1815.2021.14.053LI Chenchen, SUN Feng, SUN Meng, et al. Analysis of imbalance between supply and demand of traffic flow based on DFS algorithm and route identification[J]. Science Technology and Engineering, 2021, 21(14): 6026-6031. doi: 10.3969/j.issn.1671-1815.2021.14.053