Implementación de algoritmos de machine learning para la gestión de retransmisión de paquetes en redes FANET

Abstract

Abstract:Unmanned Aerial Vehicles (UAVs) will be an integral part of next-generation wireless communication networks. Its adoption in various fields of communication-based applications is expected to improve coverage, compared to traditional ground-based solutions. However, this new degree of freedom to be included in the network will also add new challenges. In this context, the ML Machine Learning framework is expected to provide solutions, to counter these problems. In this sense, for the development of this work, ML is used as an analysis technique to mitigate the BSP (Broadcast Storm Problem) in Ad-Hoc flight networks FANET (Flying Ad-Hoc Network). The results show that when implementing ML algorithms savings are achieved in the retransmissions of the nodes and at the same time savings in processing, time and power that is achieved by implementing these ML algorithms.