Abstract：In order to realize the scientific design of motor bus transferring scheme in the commuter corridor, the resilience recovery process of commuting corridor is regarded as a bi-level programming in which the resilience is improved through continuous exploration and iteration of ground bus transferring scheme in complex environment. The deep reinforcement learning algorithm is introduced to form the upper level planning, and the value function neural network is used to fit the response function of emergencies and travelers' cluster behavior to the adjustment of ground bus transferring scheme. The decision-making objective is achieved by training the transferring schemes. In the lower level planning, the cellular neural network model is introduced to simulate the cluster travel choice behavior under the background of data intelligence. The case study shows that this method can effectively improve the resilience of the commuter corridor, and the cluster behavior will have a negative impact on the resilience recovery.
李雪岩, 张同宇, 祝歆. 基于深度强化学习的通勤走廊韧性恢复双层规划[J]. 复杂系统与复杂性科学, 2024, 21(1): 92-99.
LI Xueyan, ZHANG Tongyu, ZHU Xin. Bi-level Programming for Resilience Restoration of Commuting Corridor Based on Deep Reinforcement Learning[J]. Complex Systems and Complexity Science, 2024, 21(1): 92-99.
[1] MURRAY T, PAMELA. A Comparison of transportation network resilience under simulated system optimum and user equilibrium conditions[C]// Proceedings of the Winter Simulation Conference WSC 2006. California, USA: Monterey, 2006: 1398-1405. [2] 张洁斐, 任刚,马景峰,等. 基于韧性评估的地铁网络修复时序决策方法[J].交通运输系统工程与信息,2020,20(4):14-20. ZHANG J F, Ren G, MA J F, et al. Decision-making method of repair sequence for metro network based on resilience evaluation [J]. Journal of Transportation Systems Engineering and Information Technology, 2020,20(4):14-20. [3] 谢永顺, 王成金, 韩增林, 等. 哈大城市带网络结构韧性演化研究[J]. 地理科学进展,2020,39(10):1619-1631. XIE Y S, WANG C J, HAN Z L, et al. Structural resilience evolution of multiple urban networks in the Harbin-Dalian urban belt[J]. Progress in Geography, 2020, 39(10): 1619-1631. [4] HUANG D, GU Y, WANG S, et al. A two-phase optimization model for the demand-responsive customized bus network design[J]. Transportation Research Part C Emerging Technologies, 2020, 111:1-21. [5] 吕彪,管心怡,高自强.地铁网络服务韧性评估与最优恢复策略[J].交通运输系统工程与信息,2021,21(5):198-205,221. LV B, GUAN X Y, GAO Z Q. Evaluation and optimal recovery strategy of metro network service resilience [J]. Journal of Transportation Systems Engineering and Information Technology, 2021,21(5):198-205,221. [6] 周日彪,庞明宝,王雄杰.基于K-shell的特大城市公交换乘优惠与线网规划协同优化[J].公路交通科技,2021,38(6):141-148. ZHOU R B, PANG M B, WANG X J. Coordination optimization of transfer pricing discount and network planning for public transport of megalopolis based on K-shell [J]. Journal of Highway and Transportation Research and Development, 2021,38(6):141-148. [7] KROESEN M. CHORUS C. A new perspective on the role of attitudes in explaining travel behavior: a psychological network model [J]. Transportation Research Part A: Policy and Practice. 2020(133):82-94. [8] 周城溪,肖玲玲. 考虑家庭成员的早高峰出行行为分析[J].系统工程理论与实践,2020,40(12):3220-3229. ZHOU C X, XIAO L L. The analysis of travel behavior during morning rush hour considering household travels [J]. Systems Engineering-Theory & Practice, 2020,40(12):3220-3229. [9] 袁韵, 徐戈, 陈晓红, 等. 城市交通拥堵与空气污染的交互影响机制研究-基于滴滴出行的大数据分析[J]. 管理科学学报,2020,23(2):54-73. YUAN Y, XU G, CHEN X H, et al. Study on the interactive mechanism of urban traffic congestion and air pollution: a big data analysis based on Di Di Chuxing [J]. Journal of Management Science in China, 2020,23(2):54-73. [10] ZHU Z, MARDAN A, ZHU S J, et al. Capturing the interaction between travel time reliability and route choice behavior based on the generalized Bayesian traffic model[J]. Transportation Research Part B: Methodological,2021(143): 48-64. [11] WANG Y, WANG Y, CHOUDHURY C. Modelling heterogeneity in behavioral response to peak avoidance policy utilizing naturalistic data of Beijing subway travelers[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2020,73:92-106. [12] 蒋阳升,刘纹滔,姚志洪.基于元胞自动机的轨道交通突发客流拥堵消散演化机理研究[J].交通运输系统工程与信息,2020,20(5):121-127. JIANG Y S, LIU W T, YAO Z H.Evolution mechanism of congestion and dissipation of sudden passenger flow in urban rail transit based on Cellular Automata [J]. Transportation Systems Engineering and Information Technology, 2020,20(5):121-127. [13] KOH S, ZHOU B, FANG H, et al. Real time deep reinforcement learning based vehicle navigation[J]. Applied Soft Computing, 2020(96): 106694. [14] 贾飞凡, 蒋熙, 李海鹰, 等. 基于强化学习的城轨信息发布策略研究[J]. 交通运输系统工程与信息, 2020, 20(5):72-78. JIA FF, JIANG X, LI H Y, et al. Information release strategy of urban rail transit based on reinforcement learning [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(5):72-78. [15] 姚恩建,张茜,张锐.公共交通票价对通勤走廊出行结构的影响[J].交通运输工程学报,2017,17(6):104-114. YAO E J, ZHANG Q, ZHANG R. Impact of public transport fare on travel mode structure of commuting corridor [J]. Journal of Traffic and Transportation Engineering, 2017,17(6):104-114. [16] TVERSKY A, KAHNEMAN D. Advances in prospect theory: cumulative representation of uncertainty [J]. Journal of Risk and Uncertainty. 1992, 5(4): 297-323. [17] PRELEC D. The probability weighting function [J]. Econometrica, 1998, 66(3): 497-527. [18] LI X Y, LI X M, YANG L R, et al. Dynamic route and departure time choice model based on self-adaptive reference point and reinforcement learning[J].Physica A: Statistical Mechanics and Its Applications, 2018, 502: 77-92.
