Collaborative Computing Optimization in Train-Edge-Cloud-Based Smart Train Systems Using Risk-Sensitive Reinforcement Learning

doi:10.1109/TVT.2023.3325674

Return

Collaborative Computing Optimization in Train-Edge-Cloud-Based Smart Train Systems Using Risk-Sensitive Reinforcement Learning

2024-03-01

PRE

DOI：10.1109/TVT.2023.3325674

Original

Original request for help

Save

Abstract

En 中文

With the advent of the intelligent and digital era, intelligent urban rail transit systems have been a research focus. As the core part of intelligent urban rail transit systems, smart trains are empowered by various intelligent applications. While improving system performance and reducing system risk, intelligent applications demand a large amount of computing power. However, it is challenging to provide simultaneously all intelligent applications for smart trains due to limited on-board computing resources. In this article, we design a train-edge-cloud (TEC) collaborative computing framework for train intelligent computing tasks. We aim to develop a TEC-based collaborative computing scheme to minimize the task processing delay with edge computing resource constraints. Considering the unique environment of smart train systems, we design a risk-sensitive reinforcement learning (RL) algorithm to realize collaborative computing optimization. We design a novel risk function in the system by jointly considering the computing load of edge intelligence (EI) servers and the characteristics of the urban rail transit systems. Moreover, we optimize the proposed risk-sensitive RL algorithm by using quantum representation and functions to accelerate its convergence speed. We design the TEC-based collaborative computing framework and design the quantum-inspired risk-sensitive RL algorithm to formulate the strategies for task scheduling. Comprehensive simulation results indicate that the algorithm adopted in this article can significantly reduce the task processing delay while satisfying EI servers' computing resource constraints. The quantum-inspired-optimized risk-sensitive RL model dramatically improves the model convergence speed.

Keywords:

Smart train systems

edge intelligence (EI)

train-edge-cloud (TEC)

collaborative computing

quantum-inspired-optimized

risk-sensitive reinforcement learning (RL)