Machine Learning Cell Throughput Prediction to Enhance Handover Processes: A Hyperparameter-Tuned Approach within the ORAN Framework

The massive number of connected devices in 5G and beyond (5G/B5G) networks has led to the emergence of ultra-dense networks (UDNs), which pose significant challenges for handover (HO) management. A critical function in wireless networks is load balancing, which ensures that traffic throughput is evenly distributed across all base stations (BS). We will go through the fundamentals and architecture of the Open Radio Access Network (O-RAN), a new concept of mobile networks built with open and interoperable Radio Access Network (RAN) components. The aim of this study is to apply hyperparameter tuning techniques, such as grid search and random search, and to conduct an in-depth exploration of the XGBoost method, focusing on objective parameters such as squared error and gamma. This paper focuses on predicting cell throughput using hyperparameter tuning in both objective methods will be mentioned in the paper to enhance predictive accuracy. The paper evaluates the model's performance using regression evaluation metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and R2 score. The study takes an initial step toward improving handover management solutions.