A Multi-Classification Machine Learning-Based Solution to Mitigate Co-Tier Interference in 5G HetNets

The exponential growth of data-hungry apps has led to an enormous increase in global data traffic. The recent worldwide pandemic has also significantly contributed to changing traffic patterns due to overloaded macrocells in the suburban residential areas, creating load balancing issues. 5G technology along with Heterogeneous Networks (HetNets), consisting of small cells, are promising solutions to address this problem. Still, the deployment of these small cells, labelled femtocells, brings a new challenge known as femtocells' co-tier interference that can hinder the performance of various 5G applications. The introduction of Machine Learning (ML)/Artificial Intelligence (AI) in the 5G architecture is considered a promising solution to tackle this issue. In this paper, we propose a machine learning-based algorithm, Machine Learning Multi-Classification and Offloading Scheme (MLMCOS) to mitigate co-tier interference in 5G HetNets. MLMCOS classifies users into multiple classes and uses a service-based-priority system to offload users experiencing co-tier interference. The proposed algorithm is compared with the classic Proportional Fair (PF) scheduling algorithm, Variable Radius and Proportional Fair scheduling (VR+PF) algorithm, and a Cognitive Approach (CA). Simulation results show that MLMCOS outperforms some existing solutions in terms of throughput, delay and Packet Loss Ratio (PLR).