5G-R Framework for High-Speed Rail Connectivity Using LSTM and Multi-Access Edge Computing

Rahmani, Shahpour; Yazdani, Nasser

doi:10.22111/ieco.2025.52762.1709

Document Type : Research Articles

Authors

Shahpour Rahmani ¹
Nasser Yazdani ²

¹ School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran Department of Computer Sciences, Faculty of Mathematics, Statistics and Computer Science, University of Sistan and Baluchestan, Zahedan, Iran

² School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran

https://doi.org/10.22111/ieco.2025.52762.1709

Abstract

High-speed rail systems, operating at speeds up to 350 km/h, face significant challenges in delivering reliable network connectivity due to frequent handovers, signal degradation, and network congestion. This paper proposes the 5G-R framework, an optimized solution integrating beamforming, network slicing, railway-specific Long Short-Term Memory (LSTM) algorithms, and Multi-Access Edge Computing (MEC) to enhance connectivity performance. By leveraging real-time train data, such as speed and GPS location, the framework optimizes handover prediction and traffic management, achieving robust performance in diverse environments. Compared to 4G LTE and standard 5G, the 5G-R framework demonstrates significant improvements, including a 250 Mbps throughput, 15 ms latency, and 95% handover success rate. Network slicing optimizes resource allocation, reducing congestion by approximately 30%, while MEC enables low-latency control for train systems. Field trials along the Beijing-Zhangjiakou railway (174 km, urban/suburban) and simulations validate the framework’s adaptability across urban and rural routes. Designed for compatibility with the Future Railway Mobile Communication System (FRMCS), the 5G-R framework lays a foundation for future advancements, including 6G and satellite communications. Future research should focus on optimizing performance in extreme environments and densely populated routes to support autonomous transport systems. This optimization-driven approach establishes a scalable model for next-generation rail communication systems.

Keywords

Main Subjects

Optimization

References

[1] W. Li, W. Chen, S. Wang, Y. Zhang, M. Matthaiou, and B. Ai, “AI-Driven Mobility Management for High-Speed Railway Communications: Compressed Measurements and Proactive Handover,” Dec. 19, 2024, doi: 10.48550/arXiv.2407.04336.

[2] Z. Yin, “Mobility Performance Analysis for Mixed Handover,” in 2024 IEEE Wireless Communications and Networking Conference (WCNC), Apr. 2024, pp. 1–6. doi: 10.1109/WCNC57260.2024.10570898.

[3] Y. Liang, H. Li, Y. Li, A. Li, Y. Wang, and D. Li, “Performance Analysis of 5G-R Network Bearing Train Control Information of HSR Based on Hardware-in-theLoop Simulation,” IEEE Access, vol. 11, pp. 60449–60461, 2023, doi: 10.1109/ACCESS.2023.3283369.

[4] S. Wang and L. Zhang, “Support vector machine-based handover scheme for heterogeneous ultra dense network of high-speed railway,” IET Commun., vol. 18, no. 18, pp. 1191–1204, 2024, doi: 10.1049/cmu2.12814.

[5] D. Jia, F. Hu, Z. Ling, Z. Mao, Z. Chang, and T. Hamalainen, “AoI-Aware Spectrum and Power Allocation for HighSpeed Railway Networks,” in 2022 14th International Conference on Wireless Communications and Signal Processing (WCSP), Nanjing, China: IEEE, Nov. 2022, pp. 544–549. doi: 10.1109/WCSP55476.2022.10039199.

[6] X. Zhao, X. Meng, and B. Wang, “Advancing Railway Systems with Next-Generation 5G Connectivity,” in 2024 International Wireless Communications and Mobile Computing (IWCMC), May 2024, pp. 357–362. doi: 10.1109/IWCMC61514.2024.10592331.

[7] Y. S. Chowdhary and G. Singh, “The Convergence of IoT and 5G: Transforming Connectivity in Smart City Applications,” in 2024 Second International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI), Aug. 2024, pp. 311–318. doi: 10.1109/ICoICI62503.2024.10696019.

[8] W. Rafique, J. Barai, A. O. Fapojuwo, and D. Krishnamurthy, “A Survey on Beyond 5G Network Slicing for Smart Cities Applications,” IEEE Commun. Surv. Tutor., pp. 1–1, 2024, doi: 10.1109/COMST.2024.3410295.

[9] R. W. Heath, N. González-Prelcic, S. Rangan, W. Roh, and A. M. Sayeed, “An Overview of Signal Processing Techniques for Millimeter Wave MIMO Systems,” IEEE J. Sel. Top. Signal Process., vol. 10, no. 3, pp. 436–453, Apr. 2016, doi: 10.1109/JSTSP.2016.2523924.

[10] R. He et al., “5G for Railways: Next Generation Railway Dedicated Communications,” IEEE Commun. Mag., vol. 60, no. 12, pp. 130–136, Dec. 2022, doi: 10.1109/MCOM.005.2200328.

[11] M. de L. Á. L. Fernández and A. P. Yuste, “Positioning of High-Speed Trains Using 5G Networks,” in 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom), Jul. 2024, pp. 221–226. doi: 10.1109/MeditCom61057.2024.10621243.

[12] Z. Kljaić, D. Pavković, M. Cipek, M. Trstenjak, T. J. Mlinarić, and M. Nikšić, “An Overview of Current Challenges and Emerging Technologies to Facilitate Increased Energy Efficiency, Safety, and Sustainability of Railway Transport,” Future Internet, vol. 15, no. 11, Art. no. 11, Nov. 2023, doi: 10.3390/fi15110347.

[13] W. Hamdi, C. Ksouri, H. Bulut, and M. Mosbah, “Network Slicing-Based Learning Techniques for IoV in 5G and Beyond Networks,” IEEE Commun. Surv. Tutor., vol. 26, no. 3, pp. 1989–2047, 2024, doi: 10.1109/COMST.2024.3372083.

[14] J. Xu, Z. Wei, Z. Lyu, L. Shi, and J. Han, “Throughput Maximization of Offloading Tasks in Multi-Access Edge Computing Networks for High-Speed Railways,” IEEE Trans. Veh. Technol., vol. 70, no. 9, pp. 9525–9539, Sep. 2021, doi: 10.1109/TVT.2021.3101571.

[15] P. Santhiya, I. J. Jebadurai, G. J. L. Paulraj, J. A, G. R. A, and S. K. Karan, “ITS-AI Integration: Enhanced Strategies for Mitigating Urban Traffic Congestion,” in 2024 5th International Conference on Recent Trends in Computer Science and Technology (ICRTCST), Apr. 2024, pp. 376–381. doi: 10.1109/ICRTCST61793.2024.10578453.

[16] J. Zhao, X. Gao, Z. Wu, Q. Zhang, and H. Han, “Artificial intelligence in rail transit wireless communication systems: Status, challenges and solutions,” Phys. Commun., vol. 67, p. 102484, Dec. 2024, doi: 10.1016/j.phycom.2024.102484.

[17] X. Gao, J. Zhao, Q. Zhang, and H. Han, “Optimization of resource allocation strategy for high-speed railway based on deep reinforcement learning,” Phys. Commun., vol. 66, p. 102455, Oct. 2024, doi: 10.1016/j.phycom.2024.102455.

[18] A. Sinha, V. Uduthalapally, D. Das, and R. Mahapatra, “SDN-Based Seamless Mobility Management for B5G Services in High-Speed Railways,” in 2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), Dec. 2023, pp. 294–299. doi: 10.1109/ANTS59832.2023.10469293.

[19] M. Fukuda, “Trend on Research and Development Relating to Information and Communication Technology in Railway Fields,” Q. Rep. RTRI, vol. 64, no. 3, pp. 161–165, 2023, doi: 10.2219/rtriqr.64.3_161.

[20] C.-X. Wang et al., “On the Road to 6G: Visions, Requirements, Key Technologies, and Testbeds,” IEEE Commun. Surv. Tutor., vol. 25, no. 2, pp. 905–974, 2023, doi: 10.1109/COMST.2023.3249835.

[21] “Integration of 5G, 6G and IoT with Low Earth Orbit (LEO) networks: Opportunity, challenges and future trends,” Results Eng., vol. 23, p. 102409, Sep. 2024, doi: 10.1016/j.rineng.2024.102409.

[22] Y. Pan, R. Li, and C. Xu, “The First 5G-LTE Comparative Study in Extreme Mobility,” Proc ACM Meas Anal Comput Syst, vol. 6, no. 1, p. 20:1-20:22, Feb. 2022, doi: 10.1145/3508040.

[23] S. Senger and P. K. Malik, “A comprehensive survey of massive-MIMO based on 5G antennas,” Int. J. RF Microw. Comput.-Aided Eng., vol. 32, no. 12, p. e23496, 2022, doi: 10.1002/mmce.23496.

[24] K. Zarzycki and M. Ławryńczuk, “LSTM and GRU neural networks as models of dynamical processes used in predictive control: A comparison of models developed for two chemical reactors,” Sensors, vol. 21, no. 16, p. 5625, Aug. 2021, doi: 10.3390/s21165625.

[25] W. Zhang, X. Li, A. Li, X. Huang, T. Wang, and H. Gao, “SGRU: A High-Performance Structured Gated Recurrent Unit for Traffic Flow Prediction,” in 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS), Dec. 2023, pp. 467–473. doi: 10.1109/ICPADS60453.2023.00076.

[26] M. Waqas and U. W. Humphries, “A critical review of RNN and LSTM variants in hydrological time series predictions,” MethodsX, vol. 13, p. 102946, Dec. 2024, doi: 10.1016/j.mex.2024.102946.

[27] J. Yang, J. Liu, J. Guo, and K. Tao, “Track Irregularity Identification Method of High-Speed Railway Based on CNN-Bi-LSTM,” Sensors, vol. 24, no. 9, Art. no. 2861, Apr. 2024, doi: 10.3390/s24092861.

[28] D. Li, S. Du, and Y. Hou, “Long-Term Passenger Flow Forecasting for Rail Transit Based on Complex Networks and Informer,” Sensors, vol. 24, no. 21, p. 6894, Jan. 2024, doi: 10.3390/s24216894.

[29] D. E. Ruíz-Guirola, O. L. A. López, S. Montejo-Sánchez, R. D. Souza, and M. Bennis, “Performance Analysis of MLBased MTC Traffic Pattern Predictors,” IEEE Wireless Communications Letters, vol. 12, no. 7, pp. 1144–1148, July 2023, doi: 10.1109/LWC.2023.3264273.

[30] K. Kosukegawa, Y. Mori, H. Suyari, and K. Kawamoto, “Spatiotemporal forecasting of vertical track alignment with exogenous factors,” Sci Rep, vol. 13, no. 1, p. 2354, Feb. 2023, doi: 10.1038/s41598-023-29303-7.

[31] A. M. Fernandes, H. I. Del Monego, B. S. Chang, and A. Munaretto, “Reducing Unnecessary Handovers Using Logistic Regression in 5G Networks,” IEEE Access, vol. 13, pp. 78707–78726, 2025, doi: 10.1109/ACCESS.2025.3564532.

[32] H. Ma, B. Lu, T. Zheng, K. Thar, and M. Gidlund, “A Gated-Guided Serial CNN-Transformer Network for HighSpeed Railway Traffic Prediction,” in 2025 IEEE 21st International Conference on Factory Communication Systems (WFCS), June 2025, pp. 1–8. doi: 10.1109/WFCS63373.2025.11077652.

[33] D. Pjanić, A. Sopasakis, A. Reial, and F. Tufvesson, “EarlyScheduled Handover Preparation in 5G NR MillimeterWave Systems,” IEEE Open Journal of the Communications Society, vol. 5, pp. 6959–6971, 2024, doi: 10.1109/OJCOMS.2024.3488594.

[34] R. Jalalifar, M. R. Delavar, and S. F. Ghaderi, “SACConvLSTM: A novel spatio-temporal deep learning-based approach for a short term power load forecasting,” Expert Systems with Applications, vol. 237, p. 121487, Mar. 2024, doi: 10.1016/j.eswa.2023.121487.

[35] B. Duan, C. Li, J. Xie, W. Wu, and D. Zhou, “Fast Handover Algorithm Based on Location and Weight in 5G-R Wireless Communications for High-Speed Railways,” Sensors, vol. 21, no. 9, Art. no. 9, Jan. 2021, doi: 10.3390/s21093100.

[36] Y. Zhou and B. Ai, “Handover schemes and algorithms of high-speed mobile environment: A survey,” Computer Communications, vol. 47, pp. 1–15, July 2014, doi: 10.1016/j.comcom.2014.04.005.

[37] GSMA, “Generic Network Slice Template,” Permanent Reference Document NG.116, Version 9.0, Apr. 2023 [Online]. Available: https://www.gsma.com/newsroom/wpcontent/uploads/NG.116-v9.0-1.pdf

[38] M. Khani, S. Jamali, M. K. Sohrabi, M. M. Sadr, and A. Ghaffari, “Slice admission control in 5G cloud radio access network using deep reinforcement learning: A survey,” International Journal of Communication Systems, vol. 37, no. 13, p. e5857, 2024, doi: 10.1002/dac.5857.

[39] Y. Ullah et al., “A survey on AI-enabled mobility and handover management in future wireless networks: key technologies, use cases, and challenges,” J. King Saud Univ. Comput. Inf. Sci., vol. 37, no. 4, p. 47, May 2025, doi: 10.1007/s44443-025-00048-9.

[40] H. Malekpoor and M. Hamidkhani, “Radiation Improvement of Low-Profile Microstrip Antenna by Utilizing AMC Surface for MIMO and Wireless Systems,” International Journal of Industrial Electronics Control and Optimization, vol. 8, no. 2, pp. 129–136, June 2025, doi: 10.22111/ieco.2024.48644.1561.

5G-R Framework for High-Speed Rail Connectivity Using LSTM and Multi-Access Edge Computing

References

References

Volume 9, Issue 3September 2026Pages 281-296

Volume 9, Issue 3
September 2026
Pages 281-296