Lightweight Machine Learning-Based QoS Optimization for Multi-UAV Emergency Communications in FANETs
Authors:
- Jonathan Javier Loor-DuqueJLJonathan Javier Loor-Duque
- Santiago Castro-AriasSantiago Castro-Arias
- Juan Pablo Astudillo LeónJLJuan Pablo Astudillo León
- Clayanela J. Zambrano-CaicedoCZClayanela J. Zambrano-Caicedo
- Iván Galo Reyes-ChacónIRIván Galo Reyes-Chacón
- Paulina VizcaínoPaulina Vizcaíno
- Leticia Lemus CárdenasLCLeticia Lemus Cárdenas
- Manuel Eugenio Morocho-CayamcelaManuel Eugenio Morocho-Cayamcela
Open Access
Abstract
Flying Ad Hoc Networks (FANETs) composed of multiple unmanned aerial vehicles (UAVs) are a promising solution for emergency wireless communications when terrestrial infrastructure is unavailable. However, ensuring reliable Quality of Service (QoS) in these highly dynamic networks remains challenging due to topology changes, varying propagation conditions, and congestion. This work proposes a lightweight machine learning-based QoS optimization framework for multi-UAV emergency communications that combines realistic mobility modeling, empirical channel measurements, and adaptive traffic prioritization. UAV mobility patterns are generated with ArduSim, while LoS/NLoS propagation models are derived from real UAV flight experiments and integrated into ns-3. Multiple supervised machine learning algorithms—including Decision Trees, Random Forest, Support Vector Machines, k-NN, Gradient Boosting, and CatBoost—are trained using four input features derived from the network state: , , , and . Simulation results show that the proposed AI SMOTE EMERGENCY scheme, based on CatBoost, improves the Packet Delivery Ratio (PDR) by approximately 43% over the No-QoS baseline, achieving 89–93% delivery across all four application ports. Compared with EDCA, the proposed scheme maintains reliable delivery for all services, increases emergency throughput by 34–36%, and reduces end-to-end delay by about 70%. In addition, the higher delivery reliability translates into clear communication energy benefits, reducing energy waste across all evaluated topologies when compared with the No-QoS baseline. The inference time remains below 0.002 s, supporting real-time QoS adaptation in resource-constrained UAV networks.
Keywords
Funding Information
- Universidad Internacional del Ecuador (GI-PPI-ME-06032024)
This publication has 35 references indexed in Scilit:
- A systematic literature review of emergency communications assisted by unnamed aerial vehiclesAd Hoc Networks, 2025
- Unmanned Autonomous Vehicles for Emergency Response and Disaster Relief2025
- Evaluation of 5G Vehicle-to-Everything (V2X) Communications in Urban Scenarios2024
- A Reinforcement Learning Congestion Control Algorithm for Smart Grid NetworksIEEE Access, 2024
- An ANOVA Based Analysis of Routing Techniques for Improving QoS in Flying Ad-Hoc Networks (FANETs)2024
- Lateral confinement of high‐impedance surface‐waves through reinforcement learningElectronics Letters, 2020
- Demonstration and application of diffusive and ballistic wave propagation for drone-to-ground and drone-to-drone wireless communicationsScientific Reports, 2020
- Towards Enhancement of Network Communication Architectures and Routing Protocols for FANETs: A Survey2020
- ArduSim: Accurate and real-time multicopter simulationSimulation Modelling Practice and Theory, 2018
- Modelling and assessing ad hoc networks in disaster scenariosJournal of Ambient Intelligence and Humanized Computing, 2012