Particle swarm optimization for airlines fleet assignment

Abstract

Airline fleet assignment is the process of assigning aircraft types to scheduled flight legs in order to minimize operating cost and achieve maximize revenue, while satisfying a set of constraints. This paper formulate the fleet assignment problem for airlines that optimization goal is to minimize the total assignment cost. Particle swarm optimization proposed to solve this model. The model successfully applied to Egyptair airline dataset using the particle swarm optimization and mixed integer programming. The proposed method compared with mixed integer programming and current Egyptair assignment methodology. The results showed that the particle swarm optimization is the best method for the Egyptair fleet assignment process. The solution quality is better than mixed integer programming and Egyptair assignment methodology where we saw a daily cost reduction with a percentage of 14.6% and 19.3% respectively.

Airlines fleet assignment prediction model for new flights using deep neural network

“…Support vector regression combined with a genetic algorithm is used by Su et al [14] to build a strong model for fleet assignment with a double-objective that maximises flight operational profit while minimising the number of aircraft types in crowded airports. Moreover, Abouzeid et al [15] have built an intelligent model to automate airlines fleet assignment process using particle swarm optimization (PSO). The model optimizes EgyptAir airlines profitability by minimizing the operating costs for available fleet types.…”