Yi, Dian (Beijing Jiaotong University), Xun, Jing (Beijing Jiaotong University), Zhao, Zicong (BeiJing JiaoTong University), Luo, Yuchen (Beijing Jiaotong University), Liu, Jin (University of Leeds)

Integrated Optimization of Speed Curve and Energy Management for a Fuel Cell Hybrid Tram on a Signalized Route

Scheduled for presentation during the Invited Session "S21b-Energy-Efficient Connected Mobility" (TH-EA-T21), Thursday, November 20, 2025, 14:10−14:30, Surfers Paradise 3

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

Fuel cell hybrid trams, recognized for zero emissions and flexibility, are facing fuel economy challenges due to the high cost of hydrogen. To minimise hydrogen consumption, this study develops a Gated Reward Mechanism (GRM) under an optimization framework integrated speed curve and energy management. By proposing the concepts of speed gate and intersection gate in a Deep Reinforcement Learning (DRL) algorithm, the tram is guided to pass through intersections during green waves, thereby achieving energy-efficient operation. Experiments are conducted under two scenarios: active Traffic Signal Priority (TSP) and Fixed Time Signal (FTS). Hydrogen consumption under active TSP is 13.5% less than that under FTS. Moreover, with the application of GRM, hydrogen consumption is reduced by 22.4% under active TSP and 25.7% under FTS.