Data-driven optimization of energy-efficient metro timetables accounting for operational deviations

Train traction energy constitutes a substantial portion (typically 40-60%) of total energy consumption in metro systems, making energy-efficient timetable optimization a crucial strategy for sustainable urban rail operations. Although existing studies have demonstrated theoretical potential in this field, their practical impact remains limited due to the common neglect of deviations between scheduled and actual timetables. This study presents a novel three-phase data-driven framework to bridge this gap. First, we establish a machine learning-enhanced simulation system to accurately reproduce actual timetables from scheduled timetables by incorporating dwell time estimation models. Second, we propose a data-driven energy calculation methodology to precisely quantify total energy consumption under real-world operating conditions. Third, a simulation-based optimization algorithm is designed to improve the energy efficiency of the operator-provided timetable through iterative refinement. Unlike prior stochastic models, our approach directly leverages real-world operational data for both timetable deviations and per-section energy profiles. Numerical experiments on a northern Chinese metro line demonstrate a simulated traction energy reduction of 5.2% (5,735 kWh), with field implementation confirming actual energy savings of 3.04% (2,646 kWh). The study provides metro operators with a replicable framework for sustainable timetable optimization, demonstrating both methodological innovation and practical energy savings.