Edge Intelligence Enhanced Monte Carlo Tree Search for Virtually Coupled Train Set Optimal Control
- 31 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (9) , 8475-8491
Abstract
Virtually Coupled Train Set (VCTS) is an advanced train control technology enabling multiple trains to operate closely through wireless communication, enhancing capacity and operational flexibility. Traditional VCTS control algorithms struggle with complex dynamic models and local optimality, hindering real-time, long-term optimization. This paper proposes an Edge Intelligence (EI) enhanced Monte Carlo Tree Search (MCTS) framework for VCTS Optimal Control (M-VOC). MCTS is a heuristic search algorithm that identifies optimal operational solutions efficiently, focusing on long-term stability over local optimums. EI supports MCTS for real-time decision-making, and we introduce a model-based reinforcement learning algorithm to manage VCTS's complex dynamics. Our framework addresses VCTS control issues in real-time while optimizing long-term benefits. To meet computational and real-time demands, we propose a train-to-edge cooperative computing strategy using multi-intelligence reinforcement learning. Simulations demonstrate that our EI-enhanced MCTS strategy effectively provides cooperative control, ensuring virtually coupled trains operate safely, stably, and punctually with reduced intervals.Keywords
Funding Information
- Beijing Jiaotong University (2024JBMC024)
- Beijing Natural Science Foundation (L241011, L221016)
- National Natural Science Foundation of China (U2368204)
- State Key Laboratory of Advanced Rail Autonomous Operation (RAO2023ZZ004)
- China Postdoctoral Science Foundation (2024M760196)
- Beijing Laboratory for Urban Mass Transit, Guangdong Laboratory of Artificial Intelligence and Digital Economy (GML-KF-24-07)
- Shenzhen Polytechnic University Postdoctoral (6024331019K)
This publication has 55 references indexed in Scilit:
- A robust MPC approach with controller tuning for close following operation of virtually coupled train setTransportation Research Part C: Emerging Technologies, 2023
- A stabilized virtual coupling scheme for a train set with heterogeneous braking dynamics capabilityTransportation Research Part C: Emerging Technologies, 2022
- Research on Virtual Coupled Train Control Method Based on GPC & VAPFChinese Journal of Electronics, 2022
- Monte Carlo Tree Search: a review of recent modifications and applicationsArtificial Intelligence Review, 2022
- A cooperative collision-avoidance control methodology for virtual coupling trainsAccident Analysis & Prevention, 2022
- Technical feasibility analysis and introduction strategy of the virtually coupled train set conceptScientific Reports, 2022
- Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms2021
- Identity Mappings in Deep Residual Networks2016
- Shift2Rail JU from Member State's Point of ViewTransportation Research Procedia, 2016
- Parallel Monte-Carlo Tree Search2008