Short term road network Macroscopic Fundamental Diagram parameters and traffic state prediction based on LSTM

Authors

DOI:

https://doi.org/10.61089/aot2024.qxx9rh86

Keywords:

multi-objective optimization, macroscopic fundamental diagram, LSTM, traffic prediction

Abstract

Macroscopic Fundamental Diagram (MFD) is widely used in traffic state evaluation due to its description of the macro level of urban road network. This study focuses on the discrimination and short-term prediction of macro traffic states in urban road networks, using MFD combined with FCM clustering for state partitioning to characterize different macro states of the road network. To predict the MFD state, this paper builds two LSTMs to perform short-term predictions on two important parameters in MFD: road network weighted flow qw and road network weighted density kw. The parameters of the first three statistical intervals and the predicted time period are used as inputs to output the MFD parameters for the predicted time period. To ensure that the two LSTM structures and hyper-parameters settings can achieve the best prediction performance for MFD, the parameter optimization process of both should be included in the same search framework for hyper-parameters search. Therefore, this paper uses GA algorithm combined with multi-objective particle swarm optimization algorithm as the solving algorithm, with the accuracy of solving two MFD parameters and the accuracy of MFD point positioning as the hyper-parameters solving objectives. The study was validated using actual road network data from Hong Kong, and the results showed that the method proposed in this paper has an MRE prediction error of less than 7.8% for the two parameters of MFD, and can predict the future temporal trend of the two parameters, demonstrating the feasibility of MFD related predictions. The model's prediction of the overall shape and change trajectory trend of MFD is consistent with reality, and some test sets in MFD state prediction show high accuracy, the overall accuracy is 81.45%. To verify the effectiveness of the multi-objective search algorithm, typical LSTM models and RNN models were used for comparison. The experiment proved that the model used in this study performed better in error control and state prediction. This study explores and practices a short-term prediction method for road network MFD parameters, MFD status, and their changing trends. Provided path reference for urban road network prediction, traffic control status, and MFD related research.

Author Biographies

  • Xuanhua Lin, College of Intelligent Transportation Engineering, Guangdong Communication Polytechnic, Guangzhou, China

    Teaching in the Intelligent Transportation Technology major at Guangdong Communication Polytechnical,  teacher, master's degree, primary title.

    Participated in multiple projects funded by the National Natural Science Foundation of China and the Provincial Natural Science Foundation of China, and led research projects in provincial universities.

  • Chaojian TAN, College of Intelligent Transportation Engineering, Guangdong Communication Polytechnic, Guangzhou, China

    Teaching in the Intelligent Transportation Technology major at Guangdong Communication Polytechnical, practical training teacher, intermediate professional title

  • Xiaohui LIN, College of Intelligent Transportation Engineering, Guangdong Communication Polytechnic, Guangzhou, China

    Teaching at the Intelligent Transportation Technology major of Guangdong Communication Polytechnic, Professor, Director of the Academic Affairs Office of the university, senior professional title, doctoral degree.Hosted two projects funded by the Natural Science Foundation of China and published more than 10 indexed articles in EI and SCI. Has multiple invention patents. Academic achievements have been included in the provincial scientific and technological achievements.

References

1. Zhengbing He, Wei Guan, Lingling Fan,&Jizhen Guan (2014) Research on the Macro Basic Map Characteristics of Beijing's Rapid Ring Road. Journal of Transportation Systems Engineering and Information Technology, 14 (2), 7. https://doi.org/10.16097/j.cnki.1009-6744.2014.02.032.

2. Wang Peng, Li Yanwen, Yang Di, et al. (2021). Macroscopic fundamental diagram traffic signal control model based on hierarchical control. Journal of Computer Applications, 41(2),571-576.

3. Godfrey, J. W. (1969). The mechanism of a road network. Traffic Engineering and Control, 11(7), 323-327.

4. Daganzo, C. F.(2007). Urban gridlock: macroscopic modeling and mitigation approaches. Transportation Research Part B: Methodological, 41B(1), p.49-62. https://doi.org/10.1016/j.trb.2006.03.001.

5. Gonzales, E. J., Chavis, C., Li, Y., & Daganzo, C. F. (2009). Multimodal transport modeling for nairobi, kenya: insights and recommendations with an evidence-based model. Institute of Transportation Studies, Research Reports, Working Papers, Proceedings.

6. Daganzo, C., Gayah, V. V.& Gonzales, E. J. (2011). Macroscopic relations of urban traffic variables: bifurcations, multivaluedness and instability. Transportation Research Part B, 45(1), 278-288. https://doi.org/10.1016/j.trb.2010.06.006.

7. Nagle, A. S., & Gayah, V. V. (2015). Comparing the use of link and probe data to inform perimeter metering control. Transportation Research Board Meeting.

8. Andrew, S., Nagle, Vikash, V., & Gayah. (2018). Accuracy of networkwide traffic states estimated from mobile probe data:. Transportation Research Record, 2421(1), 1-11. https://doi.org/10.3141/2421-01.

9. Sheng Jin, Lixiao Shen,&Zhengbing He (2018) A macro basic map model of urban road network based on multi-source data fusion. Journal of Transportation Systems Engineering and Information Technology, 18 (2), 9. https://doi.org/10.16097/j.cnki.1009-6744.2018.02.017.

10. Xiaohui Lin,&Xu Jianmin (2018) A fusion method for road network mfd estimation based on adaptive weighted average. Journal of Transportation Systems Engineering and Information Technology, 018 (006), 102-109. https://doi.org/10.16097/j.cnki.1009-6744.2018.06.015.

11. Feifei Xu, Zhaocheng He, & Zhiren Sha (2013). Impacts of Traffic Management Measures on Urban Network Microscopic Fundamental Diagram. Journal of Transportation Systems Engineering and Information Technology, 13(2), 6. https://doi.org/10.16097/j.cnki.1009-6744.2013.02.028.

12. Yongdong Jiang, Shoufeng Lu, & Liming Tao, etc(2018) The impact of exploration vehicle occupancy rate on the accuracy of macroscopic basic map estimation. Journal of Transport Science and Engineering, 34 (3): 72-77. https://doi.org/10.16544/j.cnki.cn43-1494/u.2018.03.012.

13. Jianmin Xu, Xiaowen Yan, Yingying Ma,&Yujun Wang (2018) Sensitivity analysis of Mfd to vehicle composition and calculation method of vehicle conversion coefficient. China Journal of Highway and Transport, 31 (8), 10.

14. Qingchang Lu, Han Qin, Peng Liu,&Xin Cui (2023) Analysis of new mixed traffic flow characteristics on expressways based on MFD. Journal of Southeast University Natural Science Edition, 53 (5), 905-914

15. Heng Ding, Liangyuan Zhu, Chengbin Jiang,&Xiaoyan Zheng(2018) A method for identifying the traffic status of expressway networks based on macro basic maps. Journal of Chongqing Jiaotong UniversityNatural Sciences, 37 (12), 7.

16. Chen Wen (2019), Urban Road Network Efficiency and Performance Evaluation Based on Macroscopic Fundamental Diagram(doctoral dissertation, South China University of Technology). https://doi.org/10.27151/d.cnki.ghnlu.2019.003997.

17. Yingying Ma, Shen Wen, & Zehao Jiang (2019).Sensitivity Analysis of MFD of Ring Radial Road Network on Signal Cycle. Journal of Transportation Systems Engineering and Information Technology, 19(5), 9. https://doi.org/10.16097/j.cnki.1009-6744.2019.05.011.

18. Lu, W. , Liu, J. , Mao, J. , Hu, G. , Gao, C. , & Liu, L. . (2020). Macroscopic fundamental diagram approach to evaluating the performance of regional traffic controls:. Transportation Research Record, 2674(7), 420-430. https://doi.org/10.1177/0361198120923359.

19. Lei Yu, Hongyu Zhu, Jifu Guo, Xi Zhang, Jianping Sun,&Xue Lei, et al. (2022) A Method for Calculating the Optimal Traffic Index of Road Network Theoretical Efficiency Based on MFD -- Taking Beijing as an Example. Journal of Beijing Jiaotong University Natural Science Edition (003), 046. https://doi.org/10.11860/j.issn.1673-0291.20210094.

20. Haiyan Jiang, &ZYRYANOV Vladimir (2022) Application of urban road network traffic flow analysis algorithm based on Macroscopic Fundamental Diagram. Journal of Wuhan University of Technology(Transportation Science & Engineering), 46 (6), 986-990.

21. Ruxue Li,& Lan Liu(2021) Boundary toll strategy based on MFD and distance. Journal of Highway and Transportation Research and Development, 38 (2), 139-145. https://doi.org/10.3969/j.issn.1002-0268.2021.02.018.

22. Bing Li, Hongyu Yang, Zuoxiong Zheng, Yue Feng,&Zhenghui Wang(2022) An evaluation model for the organization of prohibited left traffic based on Macroscopic Fundamental Diagram. Journal of Transportation Systems Engineering and Information Technology, 22 (3), 179-189. https://doi.org/10.16097/j.cnki.1009-6744.2022.03.020.

23. Jing, L. , & Wei, G. . (2004). A summary of traffic flow forecasting methods. Journal of Highway and Transportation Research and Development.

24. Okutani I, Stephanedes Y J. (1984). Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research Part B: Methodological, 18 (1), 1­11. https://doi.org/10.1016/0191-2615(84)90002-X.

25. Sun, S. . (2006). A bayesian network approach to traffic flow forecasting. IEEE Trans. Intelligent Transportation Systems, 7. https://doi.org/10.1109/TITS.2006.869623.

26. Castro­Neto M, Jeong Y S, Jeong M K, et al. (2009). Online­SVR for short­term traffic flow prediction under typical and atypical traffic conditions. Expert Systems with Applications, 36 (3), 6164­6173.

27. Yi H, Jung H, Bae S. (2017). Deep neural networks for traffic flow prediction. IEEE international Conference on Big Data and Smart Computing (BigComp). 328­331. https://doi.org/10.1109/BIGCOMP.2017.7881687.

28. Zhou C, Nelson P C. (2002). Predicting traffic congestion using recurrent neural networks. 9th World Congress on Intelligent Transport Systems, ITS America, ITS Japan, ERTICO (Intelligent Transport Systems and Services­Europe).

29. Hochreiter S, Schmidhuber J. (1997). Long short­term memory. Neural Computation, 9(8): 1735­1780.

30. Cho K, van Merriënboer B, Gu̇lçehre Ç, et al. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014: 1724­1734. https://doi.org/10.3115/v1/D14-1179.

31. Yanqi Ma, Qun Lin, Yucheng Zhao, Yueying Liu,&Shunyong Li (2021) Prediction of traffic flow status based on deep learning LSTM. Journal of Mathematics in Practice and Theory, 51 (4), 10.

32. Di Liang (2019) Identification and prediction of urban expressway traffic status based on taxi GPS data (Doctor dissertation, Jilin University)

33. Jia Wei (2020) Research on the prediction and evaluation method of urban road traffic operation status based on spatiotemporal characteristics (Doctoral dissertation, South China University of Technology). https://doi.org/10.27151/d.cnki.ghnlu.2020.004670.

34. Shao H, Soong B H. (2016). Traffic flow prediction with long short­term memory networks (LSTMs). IEEE Region 10 Conference (TENCON), Singapore.

35. Li Y, Yu R, Shahabi C, et al. (2018). Diffusion Convolutional Recurrent Neural Network: Data­Driven Traffic Forecasting. International Conference on Learning Representations, Vancouver

36. Lin, X., Lin, X., & Chen, K. (2022). Saturated arterial coordinate control strategy optimization considering macroscopic fundamental diagram. Archives of Transport, 62(2), 73-90. https://doi.org/10.5604/01.3001.0015.9253

37. Fujian Wang, Wei Wei, Dianhai Wang, etc (2012) Identification and Monitoring of Urban Road Network Traffic Status Based on MFD by China Intelligent Transportation Association. Excellent Paper Collection at the 7th China Intelligent Transportation Annual Conference - Intelligent Transportation Technology, 36-41

38. Shengrui Zhang, Jiangnan Lian, Shuaiyang Jiao,&Bei Zhou (2023) A short-term traffic congestion state prediction model integrating FCM-RBF. Journal of Chongqing University of Technology(Natural Science), 37 (3), 12-21.

39. Liang Ying (2022) Traffic state recognition and prediction based on vehicle trajectory data (Doctor dissertation, Southwest Jiaotong University) . https://doi.org/10.27414/d.cnki.gxnju.2022.002458.

40. Bofan Yao, Rufeng Deng, Chen Xiong,&Ming Cai (2021) Long term prediction of urban expressway traffic status based on spatiotemporal feature vectors. Journal of Sun Yat sen University Natural Science, 60(3), 115-123. https://doi.org/10.13471/j.cnki.acta.snus.2019.11.04.2019b111.

41. Xiaoyuan Feng, Zhilin Chen, Nan Ji, et al (2023) Short term traffic state prediction under predictable special events. Journal of Beijing University of Aeronautics and Astronautics, 49 (10), 2721-2730. https://doi.org/10.13700/j.bh.1001-5965.2021.0758.

42. Muyao Tang, Dake Zhou, Tao Li (2022) Deep Reinforcement Learning for Traffic Signal Control Based on State Prediction. Application Research of Computers, 39 (8), 2311-2315. https://doi.org/10.19734/j.issn.1001-3695.2021.12.0704.

43. Ruo Jia, Shenghong Dai, Ni Huang, Shuiying Li,&Zhiyuan Liu(2021) A review of research on methods for identifying traffic congestion. Journal of South China University of Technology Natural Science, 49 (4), 124-139.

44. Yongle Liu (2022) Research on Highway Traffic Flow Prediction and Traffic State Discrimination Based on Spatiotemporal Characteristics Analysis (Doctoral dissertation,Beijing Jiaotong University). https://doi.org/10.26944/d.cnki.gbfju.2022.002243.

Downloads

Published

2024-09-30

Data Availability Statement

The raw data used in this article are all from the Hong Kong government's open dataset (https://data.gov.hk/sc/), which can be downloaded from its website or through API connections. Further processing is required to obtain MFD data.

Issue

Section

Original articles

How to Cite

Xuanhua Lin, Chaojian TAN, & Xiaohui LIN. (2024). Short term road network Macroscopic Fundamental Diagram parameters and traffic state prediction based on LSTM. Archives of Transport, 71(3), 107-126. https://doi.org/10.61089/aot2024.qxx9rh86

Share

Most read articles by the same author(s)

<< < 29 30 31 32 33 34 35 36 37 38 > >> 

Similar Articles

1-10 of 245

You may also start an advanced similarity search for this article.