Analysis and Prediction of Multicell Handovers in 5G Networks Applying Logistic Regression

The evolution of wireless communication technologies brought great benefits to society, such as multi-connectivity, increased connection speed, low latency, and elevated throughput. However, it has also raised concerns regarding security and the amount of handovers to accomplish this. In this paper, we propose a low-complexity machine learning paradigm for handover prediction in 5G mobile networks by applying the Logistic Regression algorithm. By considering selection criteria like Reference Signal Received Power (RSRP), Signal to Interference and Noise Ratio (SINR), Received Signal Strength Indicator (RSSI), and distance in this algorithm, we show that it is possible to significantly reduce the number of handovers and provide a better quality of service to the user.