Performance Analysis of Support Vector Machine Learning Based Carrier Aggregation Resource scheduling in 5G Mobile Communication

Abstract

The 5G cellular system will enable heterogeneous networks that incorporate 5G, 4G, Wi-Fi, and other telecommunication connectivity. This will result in huge changes in existing infrastructure and architecture network. Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communications (URLLC), and massive Machine Type Communication (mMTC) are some of the 5G's basic application cases. The variety of heterogeneous networks makes it challenging to manage, network traffic, inter-cell, and intra-cell interfaces. Due to diverse interfaces and data transmission rates, network traffic in heterogeneous networks can be difficult to manage and control. Advanced techniques including Machine Learning (ML), Artificial Intelligence (AI), and Deep Learning (DL) are used in the 5G Network to overcome such issues. In this paper, a Support Vector Machine (SVM) learning-based resource allocation approach for heterogeneous networks is designed. A machine learning method is proposed to enhance the performance of 5G NR mobile networks. This method is used to upgrade the throughput of the overall networks. The SVM learning function detects by splitting network data of channel state information (CSI). The considered channel state data of two variables as labels with X1 and X2 and trained using SVM-LINEAR, SVM-RBF, and SVM-SIGMOID. The proposed SVM classifier by splitting data for training 80% and testing 20%. A Static Error rate is set as a threshold limit at 10% (0.10) of BLER (Block Error Rate). If the error rate passed the threshold, then update Carrier Aggregation with aggregated component else set carrier aggregation with ordinary carrier component values to Zero. The proposed approach further compares with the round robin (RR), best channel quality indicator (BCQI), fractional frequency reuse (FFR), MU-MIMO, and beamforming resource scheduling techniques. The innovative results indicated that the proposed approach enhanced spectral efficiency, average cell throughput, edge throughput peak throughput, and fairness index.