Published June 13, 2024 | Version v1
Publication Open

P4 FANET In-band Telemetry (FINT) for AI-assisted wireless link failure forecasting and recovery

Description

This paper introduces a novel framework for enhancing quality of service predictability in Flying ad hoc Networks (FANET) by leveraging P4 data-plane programmability. The proposed solution, P4 FANET In-Band Telemetry (FINT), is specifically designed to tailor the limited resources in wireless networks and is extended to collect not only the standard INT metadata but also novel essential Unmanned Aerial Vehicles (UAV) real-time metrics, including Received Signal Strength Indicator (RSSI), geolocation information and CPU load. These parameters are then fed into an artificial intelligence (AI) system, enabling proactive prediction of FANET link failures. By integrating P4 FINT and AI, our framework aims to improve the availability and overall performance of UAV-based networks through advanced link failure forecasting.

Files

P4_Fanet_INT.pdf

Files (4.7 MB)

Name Size Download all
md5:eae6d04c18a90cd3d850233e2edd4797
4.7 MB Preview Download

Additional details

Funding

DESIRE6G – Deep Programmability and Secure Distributed Intelligence for Real-Time End-to-End 6G Networks 101096466
European Commission
SMARTEDGE – Semantic Low-code Programming Tools for Edge Intelligence 101092908
European Commission