Simulation Study on Adaptive Signal Control of Deformed Intersection Based on LSTM-GNN

doi:10.16182/j.issn1004731x.joss.24-1246

Abstract

Abstract:

Aiming at the traffic congestion at deformed intersections, an improved adaptive traffic signal control scheme based on deep learning is designed, the scheme integrates the adaptive signal control of LSTM and GNN at deformed intersections. LSTM is used to capture the dependence between time series traffic data, while GNN is used to construct a spatial interaction model between lanes. By integrating the information of time and space dimensions, the model can dynamically adjust the phase duration of signal lights according to real-time traffic conditions. The results indicate that the LSTM-GNN adaptive control scheme improves overall traffic throughput efficiency by approximately 17.3% compared to traditional fixed-signal control.

Key words: deep learning, LSTM, GNN, traffic signal control, deformed intersection, adaptive control, traffic flow optimization, time-space dependence

CLC Number:

TP391

Chen Kun, Chen Liang, Xie Jiming, Liu Fengbo, Chen Taixiong, Wei Lukuan. Simulation Study on Adaptive Signal Control of Deformed Intersection Based on LSTM-GNN[J]. Journal of System Simulation, 2025, 37(6): 1343-1351.

Figures/Tables 11

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 1

Fig. 6

Table 2

Fig. 7

Fig. 8

Fig. 9

References 17

1	温保培, 邹志云, 汪锋. 组合相位在畸形交叉口信号配时中的应用——以佛山市锦华路-福禄路交叉口为例[J]. 道路交通与安全, 2006, 6(8): 22-25.
	Wen Baopei, Zou Zhiyun, Wang Feng. The Application & Research of Combinatorial Phase in Deformity Intersection[J]. Road Traffic & Safety, 2006, 6(8): 22-25.
2	姬利娜, 张金伟, 亢凤林. 城市道路畸形交叉口的交通改善方法[J]. 重庆交通大学学报(自然科学版), 2012, 31(6): 1185-1188.
	Ji Lina, Zhang Jinwei, Kang Fenglin. Traffic Improvement Method of Deformed Intersection in Urban Road[J]. Journal of Chongqing Jiaotong University(Natural Science), 2012, 31(6): 1185-1188.
3	Luo Guangzhu, Wang Jiaqi. Signal Timing Design of Malformed Intersections Based on the Change of Road Cross Angle[C]//Seventh International Conference on Electromechanical Control Technology and Transportation (ICECTT 2022). Bellingham: SPIE, 2022: 123022P.
4	孙宁, 吴伟豪, 赵风财, 等. 基于增强型Dijkstra算法的无信号灯交叉路口智能车辆调度研究[J]. 计算机应用研究, 2022, 39(1): 188-193.
	Sun Ning, Wu Weihao, Zhao Fengcai, et al. Vehicle Scheduling at Unsignalized Intersections Based on Enhanced Dijkstra Algorithm[J]. Application Research of Computers, 2022, 39(1): 188-193.
5	Kumar Neetesh, Syed Shameerur Rahman, Dhakad Navin. Fuzzy Inference Enabled Deep Reinforcement Learning-based Traffic Light Control for Intelligent Transportation System[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(8): 4919-4928.
6	舒凌洲, 吴佳, 王晨. 基于深度强化学习的城市交通信号控制算法[J]. 计算机应用, 2019, 39(5): 1495-1499.
	Shu Lingzhou, Wu Jia, Wang Chen. Urban Traffic Signal Control Based on Deep Reinforcement Learning[J]. Journal of Computer Applications, 2019, 39(5): 1495-1499.
7	徐建闽, 周湘鹏, 首艳芳. 基于深度强化学习的自适应交通信号控制研究[J]. 重庆交通大学学报(自然科学版), 2022, 41(8): 24-29.
	Xu Jianmin, Zhou Xiangpeng, Shou Yanfang. Adaptive Traffic Signal Control Based on Deep Reinforcement Learning[J]. Journal of Chongqing Jiaotong University(Natural Science), 2022, 41(8): 24-29.
8	Ma Zibo, Cui Tongchao, Deng Wenxing, et al. Adaptive Optimization of Traffic Signal Timing via Deep Reinforcement Learning[J]. Journal of Advanced Transportation, 2021, 2021(1): 6616702.
9	Huang Jianbin, Tan Qinglin, Qi Ruijie, et al. RELight: A Random Ensemble Reinforcement Learning Based Method for Traffic Light Control[J]. Applied Intelligence, 2024, 54(1): 95-112.
10	Gong Yaobang, Abdel-Aty M, Cai Qing, et al. Decentralized Network Level Adaptive Signal Control by Multi-agent Deep Reinforcement Learning[J]. Transportation Research Interdisciplinary Perspectives, 2019, 1: 100020.
11	Kumar Ritesh, Nistala Venkata Kameshwer Sharma, Chaurasiya Vijay K. Adaptive Traffic Light Control Using Deep Reinforcement Learning Technique[J]. Multimedia Tools and Applications, 2024, 83(5): 13851-13872.
12	蔡国庆, 刘玲, 张冲, 等. 基于GNN-LSTM-CNN网络的6G车辆轨迹预测算法[J]. 西安电子科技大学学报, 2023, 50(3): 50-60.
	Cai Guoqing, Liu Ling, Zhang Chong, et al. Algorithm for Prediction of the 6G Vehicle Trajectory Based on the GNN-LSTM-CNN Network[J]. Journal of Xidian University, 2023, 50(3): 50-60.
13	Regragui Younes, Moussa Najem. A Real-time Path Planning for Reducing Vehicles Traveling Time in Cooperative-intelligent Transportation Systems[J]. Simulation Modelling Practice and Theory, 2023, 123: 102710.
14	Das Debashis, Dasgupta Kousik, Biswas Utpal. A Secure Blockchain-enabled Vehicle Identity Management Framework for Intelligent Transportation Systems[J]. Computers and Electrical Engineering, 2023, 105: 108535.
15	Antonio Guillen-Perez, Maria-Dolores Cano. AIM5LA: A Latency-aware Deep Reinforcement Learning-based Autonomous Intersection Management System for 5G Communication Networks[J]. Sensors, 2022, 22(6): 2217.
16	张楠, 杨晓光. 快速路出口衔接过饱和交叉口信号优化方法[J]. 交通运输系统工程与信息, 2018, 18(6): 164-171.
	Zhang Nan, Yang Xiaoguang. Optimize Signal Timings for Oversaturated Intersections Connected with Urban Freeway Off-ramp[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(6): 164-171.
17	中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 道路交通信号灯设置与安装规范: [S]. 北京: 中国标准出版社, 2016.
	General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, Standardization Administration of the People's Republic of China. Specifications for Road Traffic Signal Setting and Installation: [S]. Beijing: Standards Press of China, 2016.

车辆位置	车道方向	车道编号	相位
由西南向东北由东北向西南	右转	-E8_0	1、2
由西南向东北由东北向西南	右转	E7_0
由西南向东北由东北向西南	直行	-E8_1
由西南向东北由东北向西南	直行	E7_1
由西南向东北由东北向西南	左转	-E8_2	3、4
由西南向东北由东北向西南	左转	E7_2	3、4
全部车道(全红时间)			5
由西向东由东向西	右转	E3_0	6、7
由西向东由东向西	右转	-E4_0
由西向东由东向西	直行	E3_1
由西向东由东向西	直行	-E4_1
由西向东由东向西	左转	E3_2	8、9
由西向东由东向西	左转	-E4_2	8、9
全部车道(全红时间)			10
由西北向东南由东南向西北	右转	E5_0	11、12
由西北向东南由东南向西北	右转	–E6_0
由西北向东南由东南向西北	直行	E5_1
由西北向东南由东南向西北	直行	–E6_1
由西北向东南由东南向西北	左转	E5_2	13、14
由西北向东南由东南向西北	左转	–E6_2	13、14
全部车道(全红时间)			15

相位	对应车道	t/s
1	E7_0, E7_1, -E8_0, -E8_1	20
2(黄灯时间)	E7_0, E7_1, -E8_0, -E8_1	3
3	E7_2, -E8_2	12
4(黄灯时间)	E7_2, -E8_2	3
5(全红时间)	所有车道	2
6	E3_0, E3_1, -E4_0,-E4_1	20
7(黄灯时间)	E3_0, E3_1, -E4_0,-E4_1	3
8	-E8_2, E7_2	12
9(黄灯时间)	-E8_2, E7_2	3
10(全红时间)	所有车道	2
11	E5_0, E5_1, -E6_0, -E6_0	20
12(黄灯时间)	E5_0, E5_1, -E6_0, -E6_0	3
13	E5_2, -E6_2	12
14(黄灯时间)	E5_2, -E6_2	3
15(全红时间)	所有车道	2

[1]	Lü Jinhu, Jiang Hongyi, Liu Deyuan, Tan Shaolin. Modeling and Simulation of Complex Systems Based on Graph Neural Networks [J]. Journal of System Simulation, 2025, 37(7): 1624-1638.
[2]	Wang Bingheng, Liu Tingrui, Yang Fan, Zhang Huan, Li Wei, Ma Ping, Yang Ming. Research on Requirements and Methods for Intelligent Assessment of Simulation Credibility [J]. Journal of System Simulation, 2025, 37(7): 1710-1722.
[3]	Wan Yuhang, Zhu Zilu, Zhong Chunfu, Liu Yongkui, Lin Tingyu, Zhang Lin. Dynamic Path Planning for Robotic Arms Based on an Improved PPO Algorithm [J]. Journal of System Simulation, 2025, 37(6): 1462-1473.
[4]	Xu Ming, Li Jinye, Zuo Dongyu, Zhang Jing. Signal Timing Optimization via Reinforcement Learning with Traffic Flow Prediction [J]. Journal of System Simulation, 2025, 37(4): 1051-1062.
[5]	Lu Xinbiao, Ye Chunlin, Chen Yisen, Wu Wen, Chen Yudan. A Transfer Learning-based Hybrid Model for PM_2.5Concentration Prediction [J]. Journal of System Simulation, 2025, 37(4): 882-894.
[6]	Jiang Dawei, Dong Yangyang, Zhang Lidong, Lu Xiao, Dong Chunxi. Research on Air Target Threat Assessment Technology Based on Deep Learning [J]. Journal of System Simulation, 2025, 37(3): 791-802.
[7]	Wang Xiao, Li Xiangyang, Liang Feng, Zhang Zhili. Research on Infrared and Visible Light Fusion Method Based on ResNet-50 and Laplacian Filtering [J]. Journal of System Simulation, 2025, 37(12): 3202-3211.
[8]	Tang Jinlin, Wang Yan, Liu Xiang, Wang Tuanjie, Ji Zhicheng. Boolean Network Model Optimization Based on Neural Network and Genetic Programming [J]. Journal of System Simulation, 2025, 37(11): 2812-2825.
[9]	Hu yang, Li Zihao, Fu Deyi, Song Ziqiu, Fang Fang, Liu Jizhen. Deep Learning Modeling of Multi-scale Characteristics of Large-scale Wind Turbine Gearbox [J]. Journal of System Simulation, 2025, 37(10): 2454-2468.
[10]	Huang Deqi, Tu Yating, Zhang Zhenhua, Guo Xin. Modeling and Simulation of Traffic Signal Control Based on MLP with Improved GCN-TD3 [J]. Journal of System Simulation, 2025, 37(10): 2568-2577.
[11]	Gu Hao, Wang Jiayu, Xiong Weili. Soft Sensor Modeling Based on Improved Transformer in Dual-stream Framework [J]. Journal of System Simulation, 2025, 37(10): 2594-2604.
[12]	Guo Yecai, Tong Shuang. A Multimodal Residual Spatial-temporal Fusion Model Based on Automatic Sleep Classification [J]. Journal of System Simulation, 2024, 36(9): 2065-2074.
[13]	Liu Zesen, Bi Sheng, Guo Chuanhong, Wang Yankui, Dong Min. Deep Learning Based Local Path Planning Method for Moving Robots [J]. Journal of System Simulation, 2024, 36(5): 1199-1210.
[14]	Wei Jinyang, Wang Keping, Yang Yi, Fei Shumin. Incremental Image Dehazing Algorithm Based on Multiple Transfer Attention [J]. Journal of System Simulation, 2024, 36(4): 969-980.
[15]	Chen Jing, Zhang Zhaochong, Wang Linkai, An Mai, Wang Wei. Short-term Bus Passenger Flow Prediction Based on Convolutional Long-short-term Memory Network [J]. Journal of System Simulation, 2024, 36(2): 476-486.