Abstract
The Permutation Flow Shop Scheduling Problem (PFSP) is a well-known combinatorial optimization problem that has been extensively studied in the literature. Traditional approaches, such as metaheuristics, have been widely used to tackle this problem, but often face limitations related to parameter selection, computational time, and the generation of initial solutions. To address these challenges, this paper proposes the utilization of two machine learning models based on the CatBoost regressor algorithm, tailored to the number of machines involved in the scheduling problem. By combining these two models with the Ant Colony Optimization (ACO) metaheuristic, we enhance its performance significantly. The first model focuses on generating high-quality initial solutions that outperform the commonly used NEH heuristic, all while maintaining computational efficiency. On the other hand, the second model is designed to expedite the enhancement of a given schedule through an efficient local search approach. To assess the efficacy of our proposed approach, we conducted extensive experiments, comparing its performance against traditional techniques using Taillard instances as benchmarks. The results of our evaluation consistently showcased the superiority of our approach, surpassing the performance of the benchmarked methods.