The Practical Application of Traffic Flow Forecasting and Capacity Analysis
DOI:
https://doi.org/10.71222/ayhgv881Keywords:
traffic flow forecast, capacity analysis, urban traffic management, traffic system optimization, road planningAbstract
With the rapid advancement of urbanization and the continuous increase in vehicle ownership, urban traffic systems are facing unprecedented pressure, leading to frequent congestion, increased travel times, and reduced overall transportation efficiency. In this context, traffic flow prediction and road capacity analysis have emerged as essential tools for modern traffic management. These technologies enable urban planners and transportation authorities to anticipate traffic trends, allocate resources more effectively, and design targeted congestion mitigation strategies. This paper conducts a comprehensive analysis of the core methodologies and key technologies involved in traffic flow forecasting and capacity evaluation, including statistical models, machine learning algorithms, and simulation-based approaches. Furthermore, the study illustrates the practical application of these technologies through real-world case studies, highlighting their role in enhancing urban mobility, reducing operational bottlenecks, and supporting the development of intelligent transportation systems (ITS). The findings suggest that scientifically grounded traffic prediction and capacity assessment not only contribute to improved traffic system performance but also lay the groundwork for data-driven urban planning and sustainable city development.
References
1. P. Redhu and K. Kumar, "Short-term traffic flow prediction based on optimized deep learning neural network: PSO-Bi-LSTM," Physica A: Stat. Mech. Appl., vol. 625, 2023, Art. no. 129001, doi: 10.1016/j.physa.2023.129001.
2. R. B. Sarooraj and S. P. Shyry, "Analysis of traffic flow prediction from spatial-temporal data using hybrid GSA-Adam opti-mizer based LSTM network for intelligent transport system," Multimedia Tools Appl., vol. 83, no. 6, pp. 16735–16761, 2024, doi: 10.1007/s11042-023-16253-5.
3. G. Petelin, R. Hribar, and G. Papa, "Models for forecasting the traffic flow within the city of Ljubljana," Eur. Transp. Res. Rev., vol. 15, no. 1, 2023, Art. no. 30, doi: 10.1186/s12544-023-00600-6.
4. B. Gomes, J. Coelho, and H. Aidos, "A survey on traffic flow prediction and classification," Intell. Syst. Appl., vol. 20, 2023, Art. no. 200268, doi: 10.1016/j.iswa.2023.200268.
5. R. Soni, P. Roy, and K. K. Nagwanshi, "WKNN-FDCNN method for big data driven traffic flow prediction in ITS," Multimedia Tools Appl., vol. 83, no. 9, pp. 25261–25286, 2024, doi: 10.1007/s11042-023-16591-4.
6. D. Bai, D. Xia, D. Huang, et al., "Spatial-temporal graph neural network based on gated convolution and topological attention for traffic flow prediction," Appl. Intell., vol. 53, pp. 30843–30864, 2023, doi: 10.1007/s10489-023-05053-x.
7. P. Brimos, et al., "Graph neural networks and open-government data to forecast traffic flow," Information, vol. 14, no. 4, 2023, Art. no. 228, doi: 10.3390/info14040228.
8. A. A. Kashyap, et al., "Traffic flow prediction models–A review of deep learning techniques," Cogent Eng., vol. 9, no. 1, 2022, Art. no. 2010510, doi: 10.1080/23311916.2021.2010510.
9. I. Shah, et al., "Forecasting day-ahead traffic flow using functional time series approach," Math., vol. 10, no. 22, 2022, Art. no. 4279, doi: 10.3390/math10224279.
10. G. Wang, "Performance evaluation and optimization of photovoltaic systems in urban environments," Int. J. New Dev. Eng. Soc., vol. 9, pp. 42–49, 2025, doi: 10.25236/IJNDES.2025.090106.
11. G. P. Mohammed, et al., "Autonomous short-term traffic flow prediction using pelican optimization with hybrid deep belief network in smart cities," Appl. Sci., vol. 12, no. 21, 2022, Art. no. 10828, doi: 10.3390/app122110828.
12. M. Patel, C. Valderrama, and A. Yadav, "Metaheuristic enabled deep convolutional neural network for traffic flow prediction: Impact of improved lion algorithm," J. Intell. Transp. Syst., vol. 26, no. 6, pp. 730–745, 2022, doi: 10.1080/15472450.2021.1974857.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Naizhong Cui (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
