A Data-driven Predictive Control Architecture for Train Thermal Energy Management

TL;DR

This paper proposes a data-driven predictive control layer for train HVAC systems to enhance energy efficiency, achieving up to 35% energy savings while maintaining passenger comfort.

Contribution

It introduces a novel middle-layer predictive control architecture using real-world data, improving energy efficiency over existing rule-based systems.

Findings

Energy savings of 10-35% demonstrated

Predictive model validated on real train coaches

Enhanced energy efficiency without compromising comfort

Abstract

We aim to improve the energy efficiency of train climate control architectures, with a focus on a specific class of regional trains operating throughout Switzerland, especially in Zurich and Geneva. Heating, Ventilation, and Air Conditioning (HVAC) systems represent the second largest energy consumer in these trains after traction. The current architecture comprises a high-level rule-based controller and a low-level tracking controller. To improve train energy efficiency, we propose adding a middle data-driven predictive control layer aimed at minimizing HVAC energy consumption while maintaining passenger comfort. The scheme incorporates a multistep prediction model developed using real-world data collected from a limited number of train coaches. To validate the effectiveness of the proposed architecture, we conduct multiple experiments on a separate set of train coaches; our results suggest energy savings between 10% and 35% with respect to the current architecture.