Optimizing 5G Quality of Service Using Machine Learning Models: A Comparative Analysis of MLR, SVR, and KNN Regression

With the rapid adoption of 5G technology, ensuring optimal quality of service (QoS) has become a critical challenge for modern wireless networks. Resource allocation in 5G networks demands advanced predictive models to balance bandwidth, latency, and application requirements effectively. This paper presents a comprehensive evaluation of three machine learning regression models—Multiple Linear Regression (MLR), Support Vector Regression (SVR), and K-Nearest Neighbors Regression (KNN)—in predicting resource allocation efficiency. Utilizing a dataset of 5G resource allocation scenarios, the models were trained and tested on features such as signal strength, latency, required bandwidth, and application type. Evaluation metrics, including R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, mean squared error (MSE), and root mean squared error (RMSE), revealed that SVR outperforms MLR and KNN in achieving higher accuracy and lower error rates. This study underscores the potential of SVR in advancing resource allocation strategies in 5G networks, paving the way for seamless, high-performance connectivity.