Genetic Algorithm–Based Column Generation Approach to Passenger Rail Crew Scheduling

Abstract

The goal of the present study was to develop and apply a genetic algorithm–based column generation heuristic to solve a passenger rail crew scheduling problem in North America. The crew scheduling problem minimized the total cost of payment to crew members on the basis of the number of hours on board, the number of hours held away from a crew base, the number of nights of lodging, and the number of onboard and away meals. Payment regulations also dictated an overtime payment and a guaranteed salary per week. Additional problem constraints included restrictions on the maximum number of continuous working hours, the maximum number of days worked per week, and the minimum number of hours of rest. The proposed heuristic produced solutions with improvements of total cost ranging from 3.0% to 27.9%.