Abstract
Purpose: The paper explores the integration of population-based methods and parallel processing techniques, particularly leveraging Apache Spark, for optimizing scheduling problems in real-world scenarios. Design/methodology/approach: Diverse population-based strategies and various improvement algorithms showcase adaptability and scalability in handling several scheduling problems. Findings: The approach is validated by computational experiments, proving its efficiency and scalability. Research limitations/implications: Future research may include finding more effective improvement algorithms, and applying machine learning techniques for managing and controlling strategies, that are used for exploration and intensification of the feasible solution space. Originality/value: The techniques outlined in the paper indicate promising directions for further study and development. Keywords: scheduling, optimization, population-based methods, parallelisation. Category of the paper: Research Paper.