Time Prediction Through A Congested Road Section

Cheng Ziyi(Mathematical Modeling Innovation Lab, North China University of Science and Technology)
Wei Ziqi(Mathematical Modeling Innovation Lab, North China University of Science and Technology)
Huang Xinhao(Mathematical Modeling Innovation Lab, North China University of Science and Technology)
Li Ying(Mathematical Modeling Innovation Lab, North China University of Science and Technology)

Abstract

First, the cellular automaton was used to simulate a "T" junction, and the correlation analysis was performed by combining the traffic pattern and the corresponding data to obtain the reason for the inaccurate prediction time of the navigation software. The collected data is preprocessed to obtain the driving time of multiple road vehicles in a week, and this is used as the influencing factor. Reuse the collected information: the length of the intersection, the average speed of real-time vehicles at the intersection, and the length of the intersection. The first two processes of the three pre-processing processes are considered together to obtain a time-dependent factor. The correlation factors and the duration of the intersections are used to predict the results of neural network training. Based on the analysis and prediction of the data, the causes of urban traffic congestion are analyzed, and measures to reduce urban congestion are proposed.

Keywords

Cellular automata; Simulation; BP neural network; Traffic jam

References

Liu Yan. Research on Urban Traffic Operation State Identification and Travel Time Forecasting Method Based on Grid Model [D]. Beijing Jiaotong University, 2018.

Huang Heyaojing, Li Ting. Research on traffic flow state based on cellular automata [J]. Urban Public Transport, 2019 (05): 40-45.

Liu Hang, Song Yingying. Application of queue length model and simulation technology in studying traffic efficiency [J]. Wireless Internet Technology, 2017 (19): 106-107.

Xiong Li, Lu Yue, Yang Shufen. Study on Prediction and Duration of Urban Road Traffic Congestion [J]. Highway, 2017, 62 (11): 125-134.

Zhang Yu. Research on Urban Road Traffic Congestion under the Background of Big Data [J]. Mechanical & Electrical Information, 2019 (29): 162-163.

Deng Jing, Zhang Qian. Traffic flow prediction based on clustering analysis and support vector machine regression [J]. Computer Knowledge and Technology, 2019, 15 (15): 13-16.

Hu Zuoan, Zou Zhengfeng, Bao Tianwen. Traffic information volume prediction method based on BP neural network [J]. Journal of Transportation Engineering and Information Technology, 2018, 16 (04): 81-87.

DOI: http://dx.doi.org/10.26549/met.v4i1.3249