Abstract
Automatic train operation (ATO) is a critical component of automatic train control (ATC) systems. The ATO automatically adjusts the speed of trains, ensuring the safety of trains and increasing the passenger capacity of urban railway networks. The traditional ATO models employ a linear approximation approach to fit the nonlinear control model of the train, such as proportional–integral–derivative (PID) or model predictive control (MPC). However, due to the complexity of actual train operations, these methods fail to accurately fit train models. Thus, they are unable to shorten the operational intervals of trains and meet the demand for improving system efficiency of ATC. In recent years, machine learning-based methods have been employed for deriving more accurate train control models. However, these methods require trains to offload massive amounts of data to central servers for centralized training, which is challenging in CBTC systems due to limited wireless bandwidth. In this paper, we propose using federated learning (FL)-based edge computing to train the ATO model without transmitting a large amount of data. The onboard computing devices are used to perform local federated learning when the train is idle. Additionally, we present a Tab-Transformer-based machine learning model for ATO policy to improve the prediction accuracy of federally trained models. Our extensive simulation results demonstrate that the proposed federated learning scheme improves the efficiency of model training, and the Tab-Transformer-based ATO model achieves better driving performance.
Similar content being viewed by others
Data availability
There are no data available.
Abbreviations
- ATC:
-
Automatic train control
- ATO:
-
Automatic train operation
- CBTC:
-
Communication-based train control
- PID:
-
Proportional–integral–derivative
- MPC:
-
Model predictive control
- FL:
-
Federated learning
- NN:
-
Neural network
- LSTM:
-
Long short-term memory
- CNN:
-
Convolutional neural networks
References
Dimitrova E, Tomov S (2021) Automatic train operation for mainline. In: 13th Electrical Engineering Faculty Conference (BulEF), Varna, Bulgaria, pp. 1–4. https://doi.org/10.1109/BulEF53491.2021.9690777
Sun X, Niu L, Yan S (2019) Mpc-pi cascade control method for heavy-haul train. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp 2527–2532
Caramia P, Lauro G, Pagano M, Natale P (2017) Automatic train operation systems: a survey on algorithm and performance index. In: 2017 AEIT International Annual Conference, pp 1–6
Yang J, Zhang Y, Jin Y (2021) Optimization of urban rail automatic train operation system based on rbf neural network adaptive terminal sliding mode fault tolerant control. Appl Syst Innov 4:51
Qiang FS, Tao H, Rui Z (2020) Ato recommended speed curve optimization based on artificial bee colony algorithm. In: 2020 5th International Conference on Information Science, Computer Technology and Transportation (ISCTT), pp 340–345
Licheng T, Tao T, Jing X, Shuai S, Tong L (2017) Optimization of train speed curve based on ato tracking control strategy. In: 2017 Chinese Automation Congress (CAC), pp 7225–7230
Zhu L, Shen C, Wang X, Liang H, Wang H, Tang T (2022) A learning based intelligent train regulation method with dynamic prediction for the metro passenger flow. IEEE Trans Intell Transp Syst 24(4):3935–3948
Wang X, Liu L, Tang T, Sun W (2019) Enhancing communication-based train control systems through train-to-train communications. IEEE Trans Intell Transp Syst 20(4):1544–1561
Liang H, Zhu L, Yu F R et al. (2023) Blockchain empowered edge intelligence for TACS obstacle detection: System design and performance optimization[J]. IEEE Transactions on Industrial Informatics
Liang H, Zhu L, Yu FR (2023) Collaborative edge intelligence service provision in blockchain empowered urban rail transit systems[J]. IEEE Internet of Things Journal
Huang Z, Liu F, Tang M, Qiu J, Peng Y (2020) A distributed computing framework based on lightweight variance reduction method to accelerate machine learning training on blockchain. China Commun 17(9):77–89
Gu R, Fan S, Hu Q, Yuan C, Huang Y (2018) Parallelizing machine learning optimization algorithms on distributed data-parallel platforms with parameter server. In: 2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS). Singapore, pp 126–133
Jeon S, et al (2018) Mapreduce tuning to improve distributed machine learning performance. In: 2018 IEEE First International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Laguna Hills, CA, USA, pp 198–200
Zhang J et al (2018) An adaptive synchronous parallel strategy for distributed machine learning. IEEE Access 6:19222–19230
Zhu L, Liang H, Wang H, Ning B, Tang T (2021) Joint security and train control design in blockchain-empowered cbtc system. IEEE Internet Things J 9(11):8119–8129
Liang H, Zhu L, Yu FR, Wang X (2022) A cross-layer defense method for blockchain empowered cbtc systems against data tampering attacks. IEEE Trans Intell Transp Syst 24(1):501–515
Liu L, Feng J, Mu X, Pei Q, Lan D, Xiao M (2023) Asynchronous deep reinforcement learning for collaborative task computing and on-demand resource allocation in vehicular edge computing. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/TITS.2023.3249745
Konečný J, McMahan HB, Yu FX, Richtárik P, Suresh AT, Bacon D(2016) Federated learning: strategies for improving communication efficiency, arXiv preprint arXiv:1610.05492
Huang X, Khetan A, Cvitkovic M et al (2020) Tabtransformer: Tabular data modeling using contextual embeddings[J]. arXiv preprint arXiv:2012.06678
De Meulemeester H, De Moor B (2020) Unsupervised embeddings for categorical variables[C]. In: International joint conference on neural networks (IJCNN). IEEE, pp. 1–8
Kuo K, Richman R (2021) Embeddings and attention in predictive modeling[J]. arXiv preprint arXiv:2104.03545
Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need[J]. Advances in neural information processing systems, 30
Li Y, Zhu L, Wang H, et al. (2023) Joint security and resources allocation scheme design in edge intelligence enabled CBTCs: a two-level game theoretic approach[J]. IEEE Transactions on Intelligent Transportation Systems
Funding
This work was supported by Beijing Natural Science Foundation (L211002).
Author information
Authors and Affiliations
Contributions
Z.Z. conceptualized the study and participated in writing original draft of the manuscript; H.J. participated in the formal analysis of the study and participated in writing original draft of the manuscript; H.Z. contributed in data or analysis tools; and Y.L. validated the results.
Corresponding author
Ethics declarations
Conflict of interest
The authors have nothing to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, Z., Jiang, H., Zhao, H. et al. Federated learning-based edge computing for automatic train operation in communication-based train control systems. J Supercomput (2024). https://doi.org/10.1007/s11227-024-06075-z
Accepted:
Published:
DOI: https://doi.org/10.1007/s11227-024-06075-z