Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network

Space–air–ground integrated network (SAGIN) has shown strong communication and computation abilities in various Internet of Things (IoTs) applications with the assistance of artificial intelligence (AI), such as emergency communication and remote sensing. However, resource heterogeneity of aerial de...

Full description

Saved in:
Bibliographic Details
Main Authors: Huibo Li, Peng Gong, Siqi Li, Weidong Wang, Yu Liu, Xiang Gao, Dapeng Oliver Wu, Duk Kyung Kim, Guangwei Zhang, Jihao Zhang
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2025-01-01
Series:Space: Science & Technology
Online Access:https://spj.science.org/doi/10.34133/space.0264
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471611311226880
author Huibo Li
Peng Gong
Siqi Li
Weidong Wang
Yu Liu
Xiang Gao
Dapeng Oliver Wu
Duk Kyung Kim
Guangwei Zhang
Jihao Zhang
author_facet Huibo Li
Peng Gong
Siqi Li
Weidong Wang
Yu Liu
Xiang Gao
Dapeng Oliver Wu
Duk Kyung Kim
Guangwei Zhang
Jihao Zhang
author_sort Huibo Li
collection DOAJ
description Space–air–ground integrated network (SAGIN) has shown strong communication and computation abilities in various Internet of Things (IoTs) applications with the assistance of artificial intelligence (AI), such as emergency communication and remote sensing. However, resource heterogeneity of aerial devices is always the bottleneck of the performance of AI models and energy efficiency. In this paper, a collaborative federated learning (FL) scheme based on device-to-device (D2D) communication in unmanned aerial vehicle (UAV)-assisted SAGIN is proposed to address the issue of heterogeneity. Aerial devices with limited communication and computation resource can offload partial nonprivacy data samples to proximity D2D pair, which can assist to train FL models. An optimization problem is proposed to minimize the total energy consumption and the loss function of local FL models. In order to solve the mixed integer nonlinear problem (MINLP), a data offloading selection strategy based on proximity discovery and an iterative method-based resource allocation algorithm (IRA) are proposed. In addition, the closed-form solutions of the optimized variables are obtained. Simulation results demonstrate that the proposed collaborative training scheme based on D2D can reduce the impact of heterogeneity on FL model performance and IRA can effectively reduce energy consumption while simultaneously enhancing training efficiency of FL.
format Article
id doaj-art-48b70142515c42f7bcbbf7b9cf89c79d
institution Kabale University
issn 2692-7659
language English
publishDate 2025-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Space: Science & Technology
spelling doaj-art-48b70142515c42f7bcbbf7b9cf89c79d2025-08-20T03:24:47ZengAmerican Association for the Advancement of Science (AAAS)Space: Science & Technology2692-76592025-01-01510.34133/space.0264Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated NetworkHuibo Li0Peng Gong1Siqi Li2Weidong Wang3Yu Liu4Xiang Gao5Dapeng Oliver Wu6Duk Kyung Kim7Guangwei Zhang8Jihao Zhang9School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.Department of Computer Science, City University of Hong Kong, Hong Kong, China.Department of Information and Communication Engineering, Inha University, Incheon, South Korea.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China.Space–air–ground integrated network (SAGIN) has shown strong communication and computation abilities in various Internet of Things (IoTs) applications with the assistance of artificial intelligence (AI), such as emergency communication and remote sensing. However, resource heterogeneity of aerial devices is always the bottleneck of the performance of AI models and energy efficiency. In this paper, a collaborative federated learning (FL) scheme based on device-to-device (D2D) communication in unmanned aerial vehicle (UAV)-assisted SAGIN is proposed to address the issue of heterogeneity. Aerial devices with limited communication and computation resource can offload partial nonprivacy data samples to proximity D2D pair, which can assist to train FL models. An optimization problem is proposed to minimize the total energy consumption and the loss function of local FL models. In order to solve the mixed integer nonlinear problem (MINLP), a data offloading selection strategy based on proximity discovery and an iterative method-based resource allocation algorithm (IRA) are proposed. In addition, the closed-form solutions of the optimized variables are obtained. Simulation results demonstrate that the proposed collaborative training scheme based on D2D can reduce the impact of heterogeneity on FL model performance and IRA can effectively reduce energy consumption while simultaneously enhancing training efficiency of FL.https://spj.science.org/doi/10.34133/space.0264
spellingShingle Huibo Li
Peng Gong
Siqi Li
Weidong Wang
Yu Liu
Xiang Gao
Dapeng Oliver Wu
Duk Kyung Kim
Guangwei Zhang
Jihao Zhang
Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network
Space: Science & Technology
title Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network
title_full Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network
title_fullStr Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network
title_full_unstemmed Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network
title_short Collaborative Federated Learning of Unmanned Aerial Vehicles in Space–Air–Ground Integrated Network
title_sort collaborative federated learning of unmanned aerial vehicles in space air ground integrated network
url https://spj.science.org/doi/10.34133/space.0264
work_keys_str_mv AT huiboli collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT penggong collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT siqili collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT weidongwang collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT yuliu collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT xianggao collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT dapengoliverwu collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT dukkyungkim collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT guangweizhang collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork
AT jihaozhang collaborativefederatedlearningofunmannedaerialvehiclesinspaceairgroundintegratednetwork