The virtually coupled train sets (VCTS) have been proposed to improve transportation efficiency, passenger satisfaction and operational capability for communication-based train control (CBTC) systems. Reliable and real-time trainto-train (T2T) wireless communications are quite desirable to ensure the stability of VCTS. Moreover, with the development of industrial Internet of Things (IIoT), an IIoT-based VCTS is proposed. Due to the physically exposed wireless environment, T2T wireless communications are vulnerable to jamming attacks (JAs), causing packets loss, time delay, and interference with the operation of VCTS systems. The distance between adjacent trains in the IIoT-based VCTS would be violate the minimum relative braking distance regulated by the traditional moving block (MB) principle if JAs were not mitigated. This is a severe safety events, which is intolerable for train control systems. In this study, we develop an event-triggered control (ETC) based resilience control method to mitigate the impact of JAs on the IIoT-based VCTS. A cooperative control approach, stable IIoT-based VCTS range and T2T communication cycle are jointly designed in the ETC-based model. The resilience control approach enables the communication cycle to be adjusted by sacrificing part of the system performance to ensure the safety and stability of VCTS systems when JAs occurs. Extensive simulation results demonstrate that the proposed ETC-based resilience control model can successfully defend against jamming attacks, and the transportation efficiency in urban rail transits can be significantly improved even under JAs.
30 September 2022 in Security and Communication Networks
The virtually coupled train sets (VCTS) have been proposed to improve operational capability and passenger satisfaction and ensure punctuality, thus alleviating the rapidly worsening traffic pressure. Recently, due to the lack of reliable wireless communications and accurate perceptual information, VCTS based on industrial internet of things (IIoT) are receiving growing concerns by integrating into the IIoT, AI, and edge computing. However, denial of service (DoS) attacks are feasible for IIoT-based VCTS due to the physically exposed open electromagnetic environment. They would cause severe safety and punctuality problems, such as poor real-time capability, enormous packet dropout rates, extensive train operational delays, and disturbance in the train convoy’s dynamic schedule. This paper deeply discusses the effects of DoS attacks on the performances of the IIoT-based VCTS by combing the physical layer with the cyber layer and explores the requirement of an attacker. We consider that the system is under the attack of a rational DoS attacker with limited jamming attacks, which will cause the most system state offset. In the paper, we propose a novel train status estimation approach to compensate for the losing information of the front train by the trade-off between the best gain of the DoS attacker and the punctuality of the IIoT-based VCTS. System performance includes physical dynamic indicators, train operational delay variance, and average waiting time of passengers. Taken together, these findings indicate that the established status estimation approach can effectively mitigate safety concerns and reduce train operational delays.
31 March 2025 in IEEE Transactions on Mobile Computing
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.
13 March 2025 in Transportation Research Part C: Emerging Technologies
Tunnel construction is a dynamic excavation process that requires a variety of construction equipment and workers to cooperate according to standard procedures. To enhance construction efficiency and reduce labor costs, intelligent construction equipments have been extensively employed in tunnel construction sites. However, the effectiveness of collaborative operation efficiency in construction equipment is hindered to some extent due to inadequate information sharing and inefficient awareness of the construction situation. To deal with the problem, we propose a cluster-based communication network architecture and define a novel metric named construction procedure coherence degree (CPCD) based on age of information (AoI) to quantify the significance of construction equipment collaborative operation. We formulate radio resource allocation as a stochastic optimization problem, which can be modeled as a decentralized partially observable Markov decision process (Dec-POMDP). Furthermore, a multi-agent reinforcement learning algorithm named QMIX is used to optimize the spectrum-sharing strategies among multiple construction equipment, enabling efficient and reliable communication. Extensive experiment results show that the QMIX outperforms well than independent Dueling DQN (IDDQN).
With the growing global demand for mineral resources, enhancing the transport capacity of heavy-haul railways (HHR) has emerged as a key area of research. As an emerging train formation technology, the virtual coupling train system (VCTS) has the potential to substantially increase the traffic density of heavy-haul trains (HHT) and thereby improve transport efficiency. However, the stable operation of virtually coupled fleets relies on train-to-train (T2T) communication, which is vulnerable to jamming attacks (JAs) within the complex operational environments of HHR. To address issues such as train decoupling and emergency braking in the VCTS that may be caused by JAs, this study proposes a stochastic game-based anti-jamming control (SGAC) strategy aimed at ensuring the stability and operational safety of the VCTS operating within HHR. The proposed approach models both JAs and defensive actions as a stochastic game and employs an -based cross-layer control method to mitigate their adverse effects. The control performance is analyzed through frequency-domain mapping, and a quantitative evaluation is conducted using the norm. The simulation results demonstrate that the SGAC scheme significantly enhances the resilience of VCTS cooperative control under JAs, offering a robust solution for ensuring the stable operation of HHR.