|
Full title—Cloud-Edge-End Collaboration for Intelligent Train Regulation Optimization in TACS
With the emergence of the next-generation train control system–Train Autonomous Circumambulation System (TACS), the transportation environment manifests obvious intricate correlations with strong couplings, multiple constraints, and rapid evolution.
In this paper, we propose a novel cloud-edge-end collaboration empowered TACS intelligent train regulation optimization scheme with situation awareness at end layer, arithmetic provision at edge layer, and intelligent fusion at cloud layer. Specifically, a Graph Convolutional Network (GCN)-based passenger flow prediction model is introduced to enable accurate assessment of the urban rail transit operation situation at the network level.
Moreover, the Deep Reinforcement Learning (DRL)-based train dynamic adjustment algorithm is proposed to ensure efficient matching of passenger and traffic flows. In addition, an Actor-Mimic based multi-task and transfer reinforcement learning method is implemented in TACS to facilitate generalizing the trained experience across multiple tasks and accelerate the ability to adapt to new environments.
Extensive simulation results illustrate that the proposed scheme can effectively improve the transportation capacity matching of TACS and enhance the generalization of train dynamic adjustment strategies.
Full Article: IEEE Transactions on Vehicular Technology, Early Access
| 
