Optimizing 5G with SVM: Analyzing Carrier Aggregation Resource Scheduling

The 5G network aims to be a game-changer in telecommunications by incorporating various network technologies like 4G and Wi-Fi. This integration calls for substantial updates to existing infrastructure. 5G is designed to support diverse applications such as Enhanced Mobile Broadband (eMBB), UltraReliable Low Latency Communications (URLLC), and Massive Machine Type Communication (mMTC). Managing such a multifaceted network is complex, but emerging technologies like Machine Learning (ML), Artificial Intelligence (AI), and Deep Learning (DL) offer solutions.This research presents a Support Vector Machine (SVM)based resource allocation strategy to boost 5G New Radio (NR) efficiency. The goal is to enhance network throughput using SVM algorithms that analyze channel state information (CSI). The data, identified by variables X1 and X2, is split into 80% for training and 20% for testing. A static Block Error Rate (BLER) of 10% is set as the threshold for adjusting Carrier Aggregation settings. Compared to existing methods like MUMIMO and Beamforming, preliminary results suggest that our SVM-based approach excels in key performance metrics such as spectral efficiency, average and peak cell throughput, edge throughput, and fairness.