Handover Prediction for NSA 5G Systems in Maritime Environments using Machine Learning

Konferenz: Mobilkommunikation - 27. ITG-Fachtagung
10.05.2023-11.05.2023 in Osnabrück

Tagungsband: ITG-Fb. 311: Mobilkommunikation – Technologien und Anwendungen

Seiten: 4Sprache: EnglischTyp: PDF

Langolf, Alexandr; Pachnicke, Stephan (Chair of Communications, Kiel University, Kiel, Germany)

The capabilities introduced by 5G enable autonomous vehicles to be deployed in a variety of different scenarios. Among these are maritime scenarios, which possess additional challenges compared to land-based scenarios, especially during the handover process. Handover prediction can be used to prepare for and possibly prevent these issues. Machine learning (ML) provides a variety of tools to accomplish this task. In this work, a long short-term memory (LSTM) and a convolutional neural network (CNN) were trained on real measurement data form a ferry. Both algorithms achieved a high prediction accuracy, with the CNN showing the best performance with a prediction accuracy of up to 94%.