This work focuses on resource allocation in cellular networks, a subject of great importance in today’s wireless communication. The purpose is to provide an overview of both old an‎d modern techniques, an‎d also to analyse the associated difficulties. Today, cellular networks support a diverse range of users an‎d devices, making resource allocation a challenging task. Traditional methods often fail to perform well, particularly in 5G an‎d 6G systems, where complexity is high, user density is dense, an‎d service deman‎d is diverse. Problems such as interference an‎d fairness are explained. Additionally, the role of Artificial Intelligence an‎d Machine Learning is described, as these can make systems more adaptive an‎d innovative in a changing environment. Different architectures, such as Heterogeneous Networks (HetNets), Cloud Radio Access Network (C-RAN), an‎d network slicing, are discussed, as they increase the challenge but also open new directions for allocation. Key performance metrics, such as throughput, fairness, energy consumption, an‎d user satisfaction, are considered, not just technical efficiency. Earlier studies from various authors are reviewed, an‎d it is demonstrated that classical optimisation alone cannot always effectively manage the problem. From this limitation, the motivation for a new AI-based approach is rising. In this report, an intelligent framework is proposed, which applies Machine Learning an‎d Reinforcement Learning for resource distribution. Several aspects, including system modelling, simulation tools, traffic patterns, an‎d user scenarios, are presented. For eva‎luation, baseline methods such as Proportional Fair, Max-SNR, DQN, an‎d greedy algorithm are used for comparison purposes. The proposed approach aims to enhance throughput, fairness, energy efficiency, an‎d service quality. Finally, it is concluded that intelligent resource allocation will be necessary for future generation wireless networks. For future research, more attention should be given to Quality of Experience, distributed learning, an‎d integration with new architectures such as Open RAN. This study aims to provide support for mobile operators an‎d researchers to develop a more efficient, fair, an‎d reliable network.

10/29/2025 12:00:00 AM

88128

1404/08/13

Overview of Resource Allocation in the Cellular Network

Resource Allocation , 6G , 4G , Heterogeneous Networks (HetNets) , 5G Networks , Cellular Network