Оптимизация отраслевых задач в управлении большими данными с использованием эволюционных алгоритмов: сравнительное исследование

Abstract

This paper proposes a novel approach to solve complex industrial big data management problems using genetic algorithms (GA), particle swarm optimization (PSO), ant algorithms (ACO) and cultural algorithms (CA). The research aims at efficient resource allocation, balancing conflicting objectives such as cost minimization, resource utilization and quality improvement. The proposed approach offers a comprehensive framework that combines the advantages of different optimization techniques, providing decision makers with important insights into optimal big data strategies in their industries. The results of the study show the effectiveness of the hybrid approach in achieving optimal decisions, which improves operational efficiency and strategic decision making in the era of big data.