网联环境中基于免疫思想的公交通行策略

doi:10.16182/j.issn1004731x.joss.22-1133

系统仿真学报 ›› 2024, Vol. 36 ›› Issue (2): 449-462.doi: 10.16182/j.issn1004731x.joss.22-1133

网联环境中基于免疫思想的公交通行策略

李操¹^,²(), 郑睿¹^,²(), 马小陆³, 丁梓琼¹^,², 仲俊屹¹^,², 张升¹^,², 齐晶晶⁴

^1.安徽师范大学物理与电子信息学院，安徽芜湖 241002
^2.安徽省智能机器人信息融合与控制工程实验室(安徽师范大学)，安徽芜湖 241002
^3.安徽工业大学电气与信息工程学院，安徽马鞍山 243000
^4.安徽达尔智能控制系统股份有限公司，安徽芜湖 241002

收稿日期:2022-09-25 修回日期:2022-11-15 出版日期:2024-02-15 发布日期:2024-02-04
通讯作者: 郑睿 E-mail:licao1102@163.com;zrwx0609@ahnu.edu.cn
第一作者简介:李操(1997-)，男，硕士生，研究方向为车联网与智能优化。E-mail：licao1102@163.com
基金资助:
安徽省科技重大专项(202003a05020028);安徽省重点研究与开发计划(202004a0502001);安徽省自然科学基金(1908085MF216);安徽省高校优秀青年支持计划(gxyq202002)

Bus Traffic Strategy Based on Immune Theory in Network Environment

Li Cao¹^,²(), Zheng Rui¹^,²(), Ma Xiaolu³, Ding Ziqiong¹^,², Zhong Junyi¹^,², Zhang Sheng¹^,², Qi Jingjing⁴

^1.School of Physics and Electronic Information, Anhui Normal University, Wuhu 241002, China
^2.Anhui Provincial Engineering Laboratory on Information Fusion and Control of Intelligent Robot (Anhui Normal University), Wuhu 241002, China
^3.School of Electrical and Information Engineering, Anhui University of Technology, Maanshan 243000, China
^4.Anhui Dar Intelligent Control System Co. Ltd, Wuhu 241002, China

Received:2022-09-25 Revised:2022-11-15 Online:2024-02-15 Published:2024-02-04
Contact: Zheng Rui E-mail:licao1102@163.com;zrwx0609@ahnu.edu.cn

摘要/Abstract

摘要：

在V2X网联环境中，公交系统能够获取全局的动态信息，以相邻公交车站之间的道路为场景开展网联公交的通行策略研究。以绿信比之差为主要参数，构建公交快速通行的数学模型；遗传算法与免疫思想相结合，设计亲和度，选取优秀抗体，提出一种混合遗传算子；改进自适应交叉、变异概率，提出一种基于免疫思想的公交通行策略。仿真结果表明：对比固定相位时长，采用遗传算法和基于免疫思想的通行策略均可较大程度地减少公交车的运行时间、等待时间和停车次数等重要指标；对比遗传算法的通行策略，基于免疫思想的通行策略绿信比变化降低了约8.8%，收敛速度提升了约26.8%，改进的策略减少了陷入局部最优的风险，能实现网联公交的快速通行，提升公交系统的运行效率。

关键词: V2X, 公交系统, 通行策略, 免疫思想, 混合遗传算子

Abstract:

In V2X network environment, the bus system can obtain dynamic global information and the bus traffic strategy is carried out based on the road scene between adjacent bus stops. The mathematical model of bus rapid traffic is constructed with the difference of green time ratio as the main parameter. A hybrid genetic operator is proposed on the basis of the combination of genetic algorithm and immune theory, the design of affinity, the selection of excellent antibodies. A bus traffic strategy based on immune theory is proposed on the basis of the improvement of adaptive crossover and mutation probability. The simulation results show that compared with the fixed phase duration, the running, waiting, and parking times can be significantly reduced by using the genetic algorithm and immune theory. Compared with the genetic algorithms for traffic strategy, the change of the green time ratio of traffic strategy based on the immune theory is reduced by about 8.8% on average, and the convergence speed is increased by about 26.8% on average. Tthe improved strategy can reduce the risk of falling into local optimum, which can realize the rapid traffic of the bus and improve the operation efficiency.

Key words: V2X, bus system, traffic strategy, immune theory, hybrid genetic operator

中图分类号:

TP18

李操,郑睿,马小陆等 . 网联环境中基于免疫思想的公交通行策略[J]. 系统仿真学报, 2024, 36(2): 449-462.

Li Cao,Zheng Rui,Ma Xiaolu,et al . Bus Traffic Strategy Based on Immune Theory in Network Environment[J]. Journal of System Simulation, 2024, 36(2): 449-462.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

表2

参考文献 33

1	徐猛, 刘涛, 钟绍鹏, 等. 城市智慧公交研究综述与展望[J]. 交通运输系统工程与信息, 2022, 22(2): 91-108.
	Xu Meng, Liu Tao, Zhong Shaopeng, et al. Urban Smart Public Transport Studies: A Review and Prospect[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(2): 91-108.
2	Liu Zicheng, Wu Naiqi, Gao Kaizhou. Urban Traffic Light Control Considering Capacity Difference Between Public Bus and Private Vehicles[J]. IEEE Access, 2021, 9: 142664-142680.
3	Sehla Khabaz, Thi Mai Trang Nguyen, Pujolle Guy, et al. Resource Allocation Modes in C-V2X: from LTE-V2X to 5G-V2X[J]. IEEE Internet of Things Journal, 2022, 9(11): 8291-8314.
4	Yuqi Lü, Wang Yunting, Liu Xiaoyong, et al. Research on Performance Testing for Urban Scenario Based on Terminal Equipment of LTE-V2X Vehicle Network[C]//2018 14th IEEE International Conference on Signal Processing (ICSP). Piscataway, NJ, USA: IEEE, 2018: 993-996.
5	Zeng Xiaosi, Zhang Yunlong, Balke K N, et al. A Real-time Transit Signal Priority Control Model Considering Stochastic Bus Arrival Time[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(4): 1657-1666.
6	凌利, 左宸, 崔嘉齐, 等. 公交车辆检测技术研究进展[J]. 现代电子技术, 2012, 35(21): 127-131.
	Ling Li, Zuo Chen, Cui Jiaqi, et al. Review of Development of Detection Techniques for Public Transport Vehicles[J]. Modern Electronics Technique, 2012, 35(21): 127-131.
7	Zhang Hu, Liang Shidong, Han Yin, et al. A Prediction Model for Bus Arrival Time at Bus Stop Considering Signal Control and Surrounding Traffic Flow[J]. IEEE Access, 2020, 8: 127672-127681.
8	李曙光, 魏靖雅, 折胜军. 考虑物理排队的自适应公交优先信号设置[J]. 长安大学学报(自然科学版), 2017, 37(1): 93-99, 126.
	Li Shuguang, Wei Jingya, She Shengjun. Adaptive Bus Priority Signal Control Considering Physical Queues[J]. Journal of Chang'an University(Natural Science Edition), 2017, 37(1): 93-99, 126.
9	乔文鑫, 王锭. 基于交叉口可靠性的公交优先信号配时优化模型[J]. 交通运输系统工程与信息, 2017, 17(2): 54-59, 67.
	Qiao Wenxin, Wang Ding. A Transit Signal Priority Optimizing Model Based on Reliability[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(2): 54-59, 67.
10	窦慧丽, 马万经, 王国华. 基于公交优先的单点交叉口车道信号协同配置模型[J]. 公路交通科技, 2019, 36(11): 75-82.
	Dou Huili, Ma Wanjing, Wang Guohua. An Integrated Lane-marking and Signal Timing Model for Isolated Intersection Based on Transit Priority[J]. Journal of Highway and Transportation Research and Development, 2019, 36(11): 75-82.
11	邓明君, 陈佳, 姚宇. 基于公交优先与综合待行区的交叉口信号控制研究[J]. 重庆交通大学学报(自然科学版), 2020, 39(8): 36-44.
	Deng Mingjun, Chen Jia, Yao Yu. Intersection Signal Control Based on Bus Priority and Comprehensive Approach Area[J]. Journal of Chongqing Jiaotong University(Natural Science), 2020, 39(8): 36-44.
12	李竹薇, 金江凯, 卢佳诚. 经济发达地区中小城市城乡公交优先发展研究[J]. 江苏科技信息, 2022, 39(1): 66-68.
	Li Zhuwei, Jin Jiangkai, Lu Jiacheng. Research on the Priority Development of Urban and Rural Public Transport in Small and Medium-sized Cities in Economically Developed Areas[J]. Jiangsu Science & Technology Information, 2022, 39(1): 66-68.
13	俞山川, 王少飞, 江维维. 重庆主城区公交专用道运行保障措施探析[J]. 重庆交通大学学报(社会科学版), 2021, 21(3): 43-49.
	Yu Shanchuan, Wang Shaofei, Jiang Weiwei. Research of Operation Support for Bus Lane in Metropolitan Area of Chongqing[J]. Journal of Chongqing Jiaotong University(Social Sciences Edition), 2021, 21(3): 43-49.
14	闫常鑫, 谢覃禹, 郭劲松. 智能网联公交信号优先技术决策前评价[J]. 交通科技与经济, 2022, 24(1): 48-56.
	Yan Changxin, Xie Tanyu, Guo Jinsong. Evaluation of the Intelligent and Connected Bus Signal Priority Technology Before Decision Making[J]. Technology & Economy in Areas of Communications, 2022, 24(1): 48-56.
15	Ma Wanjing, Ni Wei, Head L, et al. Effective Coordinated Optimization Model for Transit Priority Control Under Arterial Progression[J]. Transportation Research Record, 2013, 2366(1): 71-83.
16	杨震, 王炜, 陈淑燕, 等. 干线公交绿波通行控制中公交专用相位的设置方法[J]. 东南大学学报(自然科学版), 2014, 44(4): 854-858.
	Yang Zhen, Wang Wei, Chen Shuyan, et al. Setting Methods of Bus Exclusive Phase in Bus Green-wave Control of Urban Arterial[J]. Journal of Southeast University(Natural Science Edition), 2014, 44(4): 854-858.
17	Long Tien Truong, Currie Graham, Wallace Mark, et al. Coordinated Transit Signal Priority Model Considering Stochastic Bus Arrival Time[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(4): 1269-1277.
18	Tang Minan, Wang Qianqian, Zhang Kaiyue, et al. Signal Coordination Control of Intersection Adjacent to Main Road Based on Hybrid Automata[C]//2021 33rd Chinese Control and Decision Conference (CCDC). Piscataway, NJ, USA: IEEE, 2021: 6657-6662.
19	卢凯, 林观荣, 林永杰, 等. 考虑车流通行需求的交叉口绿信比分配模型[J]. 东南大学学报(自然科学版), 2019, 49(3): 603-610.
	Lu Kai, Lin Guanrong, Lin Yongjie, et al. Intersection Split Allocation Model Considering Traffic Flow Demand[J]. Journal of Southeast University(Natural Science Edition), 2019, 49(3): 603-610.
20	吴益源, 连培昆, 郭建钢, 等. 基于视频排队长度管理的小步增减绿信比优化方法[J]. 计算机应用, 2020, 40(6): 1842-1849.
	Wu Yiyuan, Lian Peikun, Guo Jiangang, et al. Optimization Method of Incremental Split Selection Based on Video Queue Length Management[J]. Journal of Computer Applications, 2020, 40(6): 1842-1849.
21	石荣, 刘江. 干扰资源分配问题的智能优化应用研究综述[J]. 电光与控制, 2019, 26(10): 54-61.
	Shi Rong, Liu Jiang. Application of Intelligent Optimization Methods in Jamming Resource Allocation: A Review[J]. Electronics Optics & Control, 2019, 26(10): 54-61.
22	蒋亚平, 张安康, 黎星. 人工免疫系统的研究进展与展望[J]. 信息安全与通信保密, 2021(2): 83-92.
	Jiang Yaping, Zhang Ankang, Li Xing. Research Progress and Prospect of Artificial Immune System[J]. Information Security and Communications Privacy, 2021(2): 83-92.
23	Wang Yingchen, Geng Xiaoxiao, Zhang Fan, et al. An Immune Genetic Algorithm for Multi-echelon Inventory Cost Control of IOT Based Supply Chains[J]. IEEE Access, 2018, 6: 8547-8555.
24	Ren Huizhi, Xu Han, Sun Shenshen. Immune Genetic Algorithm for Multi-objective Flexible Job-shop Scheduling Problem[C]//2016 Chinese Control and Decision Conference (CCDC). Piscataway, NJ, USA: IEEE, 2016: 2167-2171.
25	Xu Xiaoxian, Xu Pengying, Wang Yan, et al. Intelligent Design of Reconfigurable Microstrip Antenna Based on Adaptive Immune Annealing Algorithm[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14.
26	耿焕同, 孙家清, 贾婷婷. 基于自适应启动策略的混合交叉动态约束多目标优化算法[J]. 模式识别与人工智能, 2015, 28(5): 411-421.
	Geng Huantong, Sun Jiaqing, Jia Tingting. A Mixture Crossover Dynamic Constrained Multi-objective Evolutionary Algorithm Based on Self-adaptive Start-up Strategy[J]. Pattern Recognition and Artificial Intelligence, 2015, 28(5): 411-421.
27	曾松林, 余立建, 郭翠玲. 基于粒子群的城市交通信号两级模糊控制[J]. 交通科技与经济, 2013, 15(2): 88-92.
	Zeng Songlin, Yu Lijian, Guo Cuiling. Two-stage Fuzzy Control for Urban Traffic Signals Based on Particle Swarm Optimization[J]. Technology & Economy in Areas of Communications, 2013, 15(2): 88-92.
28	张雅楠, 唐阳山, 田国红, 等. 基于Python数据处理的不安全驾驶行为研究[J]. 辽宁工业大学学报(自然科学版), 2019, 39(6): 381-383, 388.
	Zhang Yanan, Tang Yangshan, Tian Guohong, et al. Study of Unsafe Driving Behaviors Based on Data Treating with Python[J]. Journal of Liaoning University of Technology(Natural Science Edition), 2019, 39(6): 381-383, 388.
29	李睿雪, 马良, 刘勇. 基于改进免疫算法的容量限制工厂选址仿真[J]. 计算机仿真, 2021, 38(12): 401-405.
	Li Ruixue, Ma Liang, Liu Yong. A New Immune Genetic Algorithm for Capacitated Plant Location Problem[J]. Computer Simulation, 2021, 38(12): 401-405.
30	Lin Jingjie, Huang S C, Jiao M K. An Evolutionary Multiobjective Carpool Algorithm Using Set-based Operator Based on Simulated Binary Crossover[J]. IEEE Transactions on Cybernetics, 2019, 49(9): 3432-3442.
31	Khalfi Souheila, Iacca Giovanni, Draa Amer. On the Use of Single Non-uniform Mutation in Lightweight Metaheuristics[J]. Soft Computing, 2022, 26(5): 2259-2275.
32	Srinivas M, Patnaik L M. Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms[J]. IEEE Transactions on Systems, Man and Cybernetics, 1994, 24(4): 656-667.
33	周帅. 城市道路交通信号控制策略的应用[J]. 黑龙江交通科技, 2020, 43(7): 232-233.

方法	决策点相位	原相位时长/s	配时后相位时长	通行时间/s	停车次数	路口等待总时长/s	绿信比差的绝对值总和	迭代次数
固定相位时长	(1, 4, 1)	(20, 20, 30, 20) (30, 25, 30, 25) (28, 25, 28, 25)		241.4	2	29.1
遗传算法的通行策略	(1, 4, 1)	(20, 20, 30, 20) (30, 25, 30, 25) (28, 25, 28, 25)	(39, 18, 18, 17) (30, 20, 25, 18) (25, 21, 24, 20)	211.3	2	3.5	0.737	38
基于免疫思想的通行策略	(1, 4, 1)	(20, 20, 30, 20) (30, 25, 30, 25) (28, 25, 28, 25)	(38, 17, 18, 17) (30, 24, 29, 24) (25, 21, 24, 23)	216.8	1	1.2	0.675	29
固定相位时长	(2, 1, 2)	(30, 25, 40, 25) (35, 20, 30, 25) (28, 25, 28, 25)		335.0	3	127.0
遗传算法的通行策略	(2, 1, 2)	(30, 25, 40, 25) (35, 20, 30, 25) (28, 25, 28, 25)	(21, 20, 27, 23) (33, 29, 37, 27) (29, 20, 30, 22)	218.6	2	6.1	0.284	31
基于免疫思想的通行策略	(2, 1, 2)	(30, 25, 40, 25) (35, 20, 30, 25) (28, 25, 28, 25)	(25, 21, 29, 21) (30, 28, 39, 26) (33, 24, 29, 24)	209.1	2	4.4	0.247	24
固定相位时长	(4, 2, 4)	(30, 35, 30, 35) (35, 25, 35, 25) (28, 20, 28, 20)		333.6	1	91.9
遗传算法的通行策略	(4, 2, 4)	(30, 35, 30, 35) (35, 25, 35, 25) (28, 20, 28, 20)	(42, 30, 31, 37) (40, 27, 40, 39) (20, 20, 21, 21)	210.7	0	1.8	0.384	38
基于免疫思想的通行策略	(4, 2, 4)	(30, 35, 30, 35) (35, 25, 35, 25) (28, 20, 28, 20)	(39, 29, 35, 39) (42, 27, 34, 36) (21, 21, 21, 21)	202.0	0	0	0.377	24

方法	决策点相位	原相位时长/s	配时后相位时长	通行时间/s	停车次数	路口等待总时长/s	绿信比差的绝对值总和	迭代次数
固定相位时长	(3)	(20, 25, 20, 30)		149.7	1	71.8
遗传算法的通行策略	(3)	(20, 25, 20, 30)	(23, 29, 24, 34)	75.5	0	0	0.016	23
基于免疫思想的通行策略	(3)	(20, 25, 20, 30)	(23, 27, 22, 33)	75.5	0	0	0.014	18
固定相位时长	(3, 3)	(25, 20, 25, 20) (35, 30, 25, 30)		203.8	1	61.9
遗传算法的通行策略	(3, 3)	(25, 20, 25, 20) (35, 30, 25, 30)	(31, 25, 29, 26) (26, 20, 27, 20)	151.7	1	3.4	0.062	36
基于免疫思想的通行策略	(3, 3)	(25, 20, 25, 20) (35, 30, 25, 30)	(29, 24, 29, 25) (24, 21, 24, 21)	150.1	1	1.9	0.059	27
固定相位时长	(4, 1)	(35, 30, 35, 35) (30, 26, 28, 20)		286.8	2	143.7
遗传算法的通行策略	(4, 1)	(35, 30, 35, 35) (30, 26, 28, 20)	(40, 34, 38, 35) (36, 31, 35, 35)	147.1	0	0	0.057	29
基于免疫思想的通行策略	(4, 1)	(35, 30, 35, 35) (30, 26, 28, 20)	(39, 33, 37, 35) (35, 30, 34, 34)	147.1	0	0	0.050	20

[1]	丁飞, 沙宇晨, 洪莹, 蒯晓, 张登银. 智能网联汽车计算卸载与边缘缓存联合优化策略[J]. 系统仿真学报, 2023, 35(6): 1203-1214.
[2]	赵传超, 郑睿, 龚莉, 马小陆. 网联环境中新能源货车的粒子群调度方法[J]. 系统仿真学报, 2023, 35(6): 1337-1350.

网联环境中基于免疫思想的公交通行策略

Bus Traffic Strategy Based on Immune Theory in Network Environment

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 33

相关文章 2

编辑推荐

Metrics

本文评价