Cost-Effective Federated Learning-Based Approach for SINR Prediction in Cellular-Connected UAVs  

作　　者：Ibrahem Mouhamad Dushantha Nalin K.Jayakody Dejan Vukobratovic 

机构地区：[1]School of Computer Science and Robotics,National Research Tomsk Polytechnic University,Tomsk 634050,Russia [2]COPELABS,Lus´ofona University,Lisbon 1749-024,Portugal [3]Faculty of Technical Sciences,University of Novi Sad,Novi Sad 21000,Serbia

出　　处：《Journal of Communications and Information Networks》2024年第4期374-389,共16页通信与信息网络学报(英文)

基　　金：supported in part by the Scheme for Promotion of Academic&Research Collaboration(SPARC),Government of India under Grant SPARC/2024-2025/NXTG/P3524;in part by the COFAC-Cooperativa de Formacao e Animacao Cultural,C.R.L.(University of Lusofona University),via the Project PortuLight(COFAC/ILIND/COPELABS/2/2023);in part by the National Funds through FCT-Fundacao para a Ciencia e a Tecnologia-as part of the project AIEE-UAV under Grant 2022.03897;PTDC,CEECINST/00002/2021/CP2788/CT0003;COPELABS under Grant UIDB/04111/2020;by the European Commission via Marie Skłodowska-Curie Actions(MSCA)as part of the Project REMARKABLE under Grant 101086387.

摘　　要：This study introduces a novel approach to empower cellular-connected unmanned aerial vehicles(UAVs)in predicting signal quality.The proposed prediction model leverages data collected by the UAVs,addressing privacy concerns and ensuring effectiveness,while taking into account the constraints of UAVs.A unique three-step approach is proposed,which integrates a detailed physical ray-tracing(RT)method,deep learning,and federated learning(FL)for continuous learning and field adaptation.A dual input feature fusion convolutional neural network(DIFF-CNN)model is proposed,which is pretrained on RT data and fine-tuned using data collected by the UAVs via FL.The proposed model demonstrates superior performance and robustness to data sparsity compared to traditional machine learning algorithms.Notably,the model achieves a root mean squared error of 0.837 dB and an R-squared of 97.7% for signal-to-interference-plus-noise ratio(SINR)prediction after the fine-tuning step in the fixed-altitude scenario,but performance drops with uniform altitude distribution,highlighting the impact of flying height on fine-tuning.The research indicates that the proposed approach can enhance performance while reducing training rounds by 35% to 90%,thus mitigating FL overheads.Future research could explore efficiency gains by using different pretrained models tailored to specific flying heights.

关 键 词：federated learning unmanned aerial vehicle convolutional neural network RAY-TRACING signal-tointerference-plus-noise ratio 

分 类 号：TN929.5[电子电信—通信与信息系统]