A data-driven bi-objective matheuristic for energy-optimising timetables in a passenger railway network

Abstract

Energy-efficient train timetabling (EETT) is essential to achieve the full potential of energy-efficient train control, which can reduce operating costs and contribute to a reduction in CO${}_2$ emissions. This article proposes a bi-objective matheuristic to address the EETT problem for a railway network. To our knowledge, this article is the first to suggest using historical data from train operation to model the actual energy consumption, reflecting the different driving behaviours. The matheuristic employs a genetic algorithm (GA) based on NSGA-II. The GA uses a warm-start method to generate the initial population based on a mixed-integer program. A greedy first-come-first-served fail-fast repair heuristic is used to ensure feasibility throughout the evolution of the population. The objectives taken into account are energy consumption and passenger travel time. The matheuristic was applied to a real-world case from a large North European train operating company. The considered network consists of 107 stations and junctions, and 18 periodic timetables for 9 train lines. Our results show that for an entire network, a reduction up to 3.3% in energy consumption and 4.64% in passenger travel time can be achieved. The results are computed in less than a minute, making the approach suitable for integration with a decision support tool.