A New Effective Strategy for User Association in Heterogeneous Networks

Heterogeneous networks (HetNet) represent a promising technology that satisfies the needs of mobile users. However, several problems have influenced the performance of wireless communication, such as the maximization of energy efficiency and the problem of interferences due to the uncontrolled association of the user equipment (UE). Solving the problem of maximizing energy efficiency has captured the attention of several researchers. In this work, we propose an effective user association based on K-nearest Neighbors (KNN) approach considering a large dataset. The major novelty of this work is that the supervised learning perspective is applied to a dataset regrouped from an optimal user association, where the most valuable parameters are considered. Additionally, it allows for mitigating the problem of interferences using individual user association. Simulation results have proven the efficiency of the proposed methodology The suggested results have outperformed the two works in terms of accuracy, where the proposed method presents a better accuracy of 95%.