Koopman-based Prediction of Connectivity for Flying Ad Hoc Networks

Abstract--The application of machine learning (ML) to communication systems is expected to play a pivotal role in future artificial intelligence (AI)-based next-generation wireless networks. While most existing works focus on ML techniques for static wireless environments, they often face limitations when applied to highly dynamic environments, such as flying ad hoc networks (F ANETs). This paper explores the use of data-driven Koopman approaches to address these challenges. Specifically, we investigate how these approaches can model UA V trajectory dynamics within F ANETs, enabling more accurate predictions and improved network performance. By leveraging Koopman operator theory, we propose two possible approaches--centralized and distributed--to efficiently address the challenges posed by the constantly changing topology of F ANETs. Our results show that these approaches can accurately predict connectivity and isolation events that lead to modelled communication outages. This capability could help UA Vs schedule their transmissions based on these predictions.