Koopman-based Prediction of Connectivity for Flying Ad Hoc Networks

2025-11-03

AI Summary

In Flying Ad-hoc Networks (FANETs), highly dynamic topologies severely degrade communication reliability. Method: This paper introduces, for the first time, the data-driven Koopman operator theory to model and predict FANET connectivity. We propose both centralized and distributed Koopman-based prediction frameworks that learn nonlinear dynamical patterns of UAV trajectory evolution, enabling high-accuracy, proactive forecasting of network connectivity, isolated nodes, and link interruptions. Additionally, the framework infers time-varying Signal-to-Interference-plus-Noise Ratio (SINR) trends to support optimized communication scheduling. Contribution/Results: Experimental evaluation in a predefined monitoring scenario demonstrates significant improvement in interruption early-warning accuracy. The approach provides both theoretical foundations and practical tools for adaptive transmission in highly dynamic environments, advancing the state-of-the-art in FANET resilience and predictive networking.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Application Domains: Mobility, Driving & Flight
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

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 (FANETs). This paper explores the use of data-driven Koopman approaches to address these challenges. Specifically, we investigate how these approaches can model UAV trajectory dynamics within FANETs, 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 FANETs. To demonstrate this, we consider a FANET performing surveillance with UAVs following pre-determined trajectories and predict signal-to-interference-plus-noise ratios (SINRs) to ensure reliable communication between UAVs. Our results show that these approaches can accurately predict connectivity and isolation events that lead to modelled communication outages. This capability could help UAVs schedule their transmissions based on these predictions.

Problem

• Predicting connectivity in dynamic flying ad hoc networks
• Modeling UAV trajectory dynamics using Koopman operator theory
• Addressing communication outages through accurate SINR prediction

Innovation

• Koopman operator theory models UAV trajectory dynamics
• Centralized and distributed approaches predict network connectivity
• Data-driven methods forecast SINR for reliable FANET communication