Análisis del proceso de handover en una red macrofemtocelular 5G basado en técnicas de M

Abstract

Abstract: The following thesis analyzes the handover process in heterogeneous cellular networks, where the demand for efficiency and metrics management has driven the application of new techniques such as machine learning (ML)-based algorithms. The main objective of this work is to simulate a 5G macro-femtocellular network with two different mobility models and compare their performance based on a standard handover process and a handover process based on two separate ML techniques. This study determines which of the two techniques is more effective for handover decision-making. A quantitative methodology was implemented, using a decision algorithm based on the RSRP threshold for handover and simulating the network to generate a dataset that allowed training the two ML techniques and subsequently applying them in the same simulation for comparison in the three scenarios. The analysis showed that the integration of ML, especially neural networks, effectively optimizes the handover process.