A bi-objective optimization approach for scheduling electric ground-handling vehicles in an airport

To reduce airport operating costs and minimize environmental pollution, converting ground-handling vehicles from fuel-powered to electric ones is inevitable. However, this transformation introduces complexity in scheduling due to additional factors, such as battery capacities and charging requirements. This study models the electric ground-handling vehicle scheduling problem as a bi-objective integer programming model to address these challenges. The objectives of this model are to minimize the total travel distance of vehicles serving flights and the standard deviation of the total occupancy time for each vehicle. In order to solve this model and generate optimal scheduling solutions, this study combines the non-dominated sorting genetic algorithm 2 (NSGA2) with the large neighborhood search (LNS) algorithm, proposing a novel NSGA2-LNS algorithm. A dynamic priority method is used by the NSGA2-LNS to construct the initial population, thereby speeding up the convergence. The NSGA2-LNS employs the LNS algorithm to overcome the problem that metaheuristic algorithms often lack clear directions in the process of finding solutions. In addition, this study designs the correlation-based destruction operator and the priority-based repair operator in the NSGA2-LNS algorithm, thereby significantly enhancing its ability to find optimal solutions for the electric ground-handling vehicle scheduling problem. The algorithm is verified using flight data from Chengdu Shuangliu International Airport and is compared with manual scheduling methods and traditional multi-objective optimization algorithms. Experimental results demonstrate that the NSGA2-LNS can rapidly solve the scheduling problem of allocating electric ground-handling vehicles for hundreds of flights and produce high-quality scheduling solutions.