With the development of wireless technologies and the increase in the number of connected devices, there is an urgent need to improve the efficiency of wireless networks. One of the promising areas for solving this problem is the use of artificial intelligence (AI) algorithms that allow adaptive management of network resources in a changing environment and a variety of user requests. This paper analyzes existing machine learning and deep learning algorithms applicable to wireless network resource management, including regression, classification, clustering and reinforcement learning methods. The advantages and disadvantages of each approach are presented, and the choice of the most relevant and accessible models for practical implementation is substantiated. Particular attention is paid to the possibility of dynamic channel width management, frequency range distribution and interference reduction by predicting traffic and network status. It is shown that the implementation of AI algorithms can significantly improve the quality of service (QoS) and user satisfaction, especially in conditions of high device density and signal instability. The work can serve as a basis for further research and development of prototypes of next-generation adaptive wireless networks.
Akhmetshina et al. (2025) studied this question.