Su, Dongling (Beijing Jiaotong University), Bu, Bing (Beijing Jiaotong University)

Adaptive Optimization Method of Train-Ground Wireless Communication Network Coverage for Urban Rail Transit

Scheduled for presentation during the Invited Session "S16a-Control, Communication and Emerging Technologies in Smart Rail Systems" (TH-LM-T16), Thursday, November 20, 2025, 11:50−12:10, Southport 1

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

The quality of service (QoS) of wireless communications affects the efficiency of train operations since the communication-based train control system (CBTC) relies on the train-ground (T2G) wireless communication network to transmit critical data. This paper models the relationships between communication latency, packet loss, train tracking interval, and the probability of triggering unnecessary braking (PTUB) to quantify the impact of QoS on train operation efficiency. Considering the characteristics of urban rail transit T2G communication scenarios, a method of coverage optimization based on multi-agent deep deterministic policy gradient (MADDPG) is proposed, and the PTUB measures the coverage quality. The simulation results show that the proposed method can reduce the average latency from 34.007 ms to 24.779 ms, the average packet loss rate from 2.31% to 1.18%, and the PTUB in 98% of the time slots from 3.39% to 0.21%, effectively improving the coverage quality.