Real-time metro train rescheduling under uncertainties: A hybrid machine learning and integer L-shaped approach

Key Points

• Real-time scheduling effectively manages uncertainties in metro train operations, improving overall reliability.
• Utilizing machine learning models, the approach targets improved decision-making under variable conditions and constraints.
• This research combines integer programming techniques with real-time adjustments, leading to optimized train schedules.
• Findings may suggest broader applications in public transport systems, highlighting a need for robust adaptive frameworks.