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

被引：0

作者：

Ismail, Layal ^{[1
]}

Uomo, Domenico ^{[1
]}

Sgambelluri, Andrea ^{[1
]}

Alhamed, Faris ^{[1
]}

Paolucci, Francesco ^{[2
]}

机构：

[1] Scuola Super Sant Anna, Via G Moruzzi 1, I-56124 Pisa, Italy

[2] CNIT, Via G Moruzzi 1, I-56124 Pisa, Italy

来源：

COMPUTER NETWORKS | 2024年 / 250卷

关键词：

SD-FANET; AI; P4; Language; LOCALIZATION; CHALLENGES; NETWORKING; ALGORITHM;

D O I：

10.1016/j.comnet.2024.110599

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

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.

引用

页数：17