Abstract
This paper examines task distribution optimization methods in IT systems using metaheuristic algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO). The study explores their applicability to solve complex problems in modern IT environments, where traditional methods fail to efficiently process large data volumes or provide the required accuracy. The research focuses on IT systems that need optimal allocation of computational and human resources to enhance performance and reduce costs. Mathematical models for dynamic optimization are developed, considering parameters such as cost, time, and quality of task execution. A comparative analysis of the three methods (GA, PSO, ACO) showed that each has its strengths and weaknesses in the context of optimization tasks: GA is most effective in terms of time but with higher costs, while PSO and ACO deliver better results in quality with lower time and memory costs. The practical value of the research lies in the potential application of the proposed methods for automating resource management processes in IT, significantly improving operational efficiency and reducing costs. The scientific value of the work is in expanding theoretical approaches to using metaheuristic methods to solve optimization problems in IT services and project management.