Swarm Intelligence Algorithms for Solving Optimization Problems in Telecommunication Systems
Leonid S. Adonin, Andrei G. Vladyko · Proceedings of Telecommunication Universities · 2025
Relevance. In the modern world, telecommunications play a critically important role in supporting the digital economy. The complexity and scale of contemporary telecommunication networks ‒ characterized by high dynamism, heterogeneity, and continuously growing traffic ‒ necessitate the development and application of efficient optimization methods. Traditional analytical approaches often prove inadequate in addressing the combinatorial complexity and nonlinearity of problems arising in this domain, making the search for alternative solutions increasingly relevant. In this context, swarm intelligence algorithms represent a promising class of methods inspired by the collective behavior of biological organisms, capable of effectively solving complex optimization tasks. The aim of this study is to systematize and analyze current research devoted to the application of swarm intelligence algorithms in telecommunication networks. Particular attention is given to such methods as the Artificial Bee Colony (ABC) algorithm, Ant Colony Optimization (ACO), and the Grey Wolf Optimizer (GWO), as well as their modifications. The main objective of the research is to identify key trends and development directions of heuristic algorithms aimed at enhancing the performance, reliability, and resilience of telecommunication systems under increasing traffic loads and evolving network architectures. Scientific novelty lies in conducting a systematic review of recent publications focusing on the practical application of swarm intelligence algorithms in the field of telecommunications. A taxonomy of the considered methods is presented, and their core operational principles and effectiveness in solving specific optimization problems within this domain are analyzed. Special emphasis is placed on the adaptation and hybridization of algorithms to improve their performance in real-world network scenarios. The theoretical significance of the study consists in summarizing existing practices of applying bio-inspired optimization techniques in telecommunications, thereby opening up opportunities for further development of more efficient and scalable approaches to managing complex dynamic systems. The obtained results contribute to a deeper understanding of the potential of swarm intelligence algorithms in solving routing, resource allocation, network planning, and other critical problems typical of the modern digital economy.