基于选举策略的低空物联网稳定联邦学习方法

申凌峰; 王光辉; 白天水; 朱政宇; 张千坤

doi:10.11959/j.issn.2096-3750.2024.00415

您当前的位置：

首页 >

文章列表页 >

基于选举策略的低空物联网稳定联邦学习方法

理论与技术 | 更新时间：2025-03-13

- 基于选举策略的低空物联网稳定联邦学习方法
- Stable federated learning method for low-altitude IoT networks based on election strategy
- 物联网学报 2024年8卷第3期页码：55-65
- 作者机构：
  
  1.河南大学软件学院，河南开封 475004
  2.河南省智能网络理论与关键技术国际联合实验室，河南开封 475004
  3.郑州大学电气与信息工程学院，河南郑州 450001
  4.中迅邮电咨询设计院有限公司，北京 100048
- 作者简介：
  
  [ "申凌峰（1992‒ ），男，博士，河南大学软件学院讲师、硕士生导师，主要研究方向为无人机通信、物联网、联邦学习等。" ]
  [ "王光辉（1987‒ ），男，博士，河南大学软件学院副教授、硕士生导师，主要研究方向为物联网、联邦学习与智能交通等。" ]
  [ "白天水（1995‒ ），男，河南大学软件学院硕士生，主要研究方向为物联网技术、联邦学习。" ]
  [ "朱政宇（1988‒ ），男，博士，郑州大学电气与信息工程学院副教授、博士生导师，主要研究方向为智能无线通信及应用。" ]
  [ "张千坤（1992‒ ），男，中讯邮电咨询设计院有限公司工程师，主要研究方向为物联网、高精度定位与智能网络等。" ]
- 基金信息：
  
  国家自然科学基金重大研究计划(92367302);河南省科技攻关项目(242102210139;242102211097);河南省高等学校重点科研项目(25A510015;25A520008);河南省交通运输厅科技项目(2023-3-2)
- DOI：10.11959/j.issn.2096-3750.2024.00415
  中图分类号：
- 收稿日期：2024-08-26，
  
  修回日期：2024-09-15，
  
  纸质出版日期：2024-09-10
- 稿件说明：
移动端阅览
申凌峰,王光辉,白天水等.基于选举策略的低空物联网稳定联邦学习方法[J].物联网学报,2024,08(03):55-65.

SHEN Lingfeng,WANG Guanghui,BAI Tianshui,et al.Stable federated learning method for low-altitude IoT networks based on election strategy[J].Chinese Journal on Internet of Things,2024,08(03):55-65.
申凌峰,王光辉,白天水等.基于选举策略的低空物联网稳定联邦学习方法[J].物联网学报,2024,08(03):55-65. DOI： 10.11959/j.issn.2096-3750.2024.00415.

SHEN Lingfeng,WANG Guanghui,BAI Tianshui,et al.Stable federated learning method for low-altitude IoT networks based on election strategy[J].Chinese Journal on Internet of Things,2024,08(03):55-65. DOI： 10.11959/j.issn.2096-3750.2024.00415.

摘要

随着无人机（UAV

unmanned aerial vehicle）与物联网（IoT

Internet of things）技术的深度融合，低空物联网中传输了大量包含敏感信息的数据，存在严重的隐私泄露风险。联邦学习（FL

federated learning）允许多个参与者共同训练模型而无须共享敏感数据，为低空物联网安全应用提供了隐私保护的方案。但是，随着应用场景越来越丰富，节点异构性、网络动态性等特点导致低空物联网下的联邦学习非常不稳定。提出了一种结合Raft选举算法和权重计算的新型联邦学习方法（FedPRE-W

federated fearning based on proxy Raft election and weight calculation），提高了联邦学习的稳定性和效率。针对遮挡、网络动态变化以及节点能量耗尽等导致的代理设备中断问题，通过Raft选举算法选举新的代理设备，保障联邦学习的稳定性。结合节点异构性，通过计算节点权重，选举性能强的节点当选代理，提升了联邦学习的效率。最后，在公开数据集上对所提方法进行验证，结果显示，FedPRE-W算法在减少通信轮数、加速模型收敛以及提高系统稳定性等方面有显著优势。该方法为低空物联网进行安全、稳定、高效的联邦学习提供了一种可行的解决方案。

Abstract

The deep integration of UAV and Internet of things (IoT) transmits a large amount of sensitive data in the air-to-ground intelligent network

posing a serious risk of privacy leakage. The proposal of federated learning (FL) provides a privacy-preserving solution for low-altitude IoT applications

allowing multiple participants to jointly train models without sharing sensitive data. However

the federated learning performance is unstable because of various application scenarios

heterogeneous nodes and dynamic environments. An federated fearning based on proxy Raft election and weight calculation (FedREP-W) method was proposed

which combined classical Raft election and weight calculation

significantly improving the stability and efficiency of federated training. To be more specific

the use of Raft to choose new agent devices keeped federated learning stable. By incorporating the concept of weight elections

the effectiveness of federated learning could be enhenced by designating the most powerful node as an agent. The experimental results publicly available datasets show that the proposed strategy and algorithm perform well in lowering the number of communication rounds

speeding up model convergence

and making the system stable. This provides a feasible solution for efficient

secure

and stable federated learning in low-altitude IoT networks.

关键词

Keywords

references

WANG J Y , SU D P , FENG P , et al . Optimal height of UAV in covert visible light communications [J ] . IEEE Communications Letters , 2023 , 27 ( 10 ): 2682 - 2686 .

DO Q T , SHUMEYE LAKEW D , TIEN TRAN A , et al . A review on recent approaches in mmWave UAV-aided communication networks and open issues [C ] // Proceedings of the 2023 International Conference on Information Networking (ICOIN) . Piscataway : IEEE Press , 2023 : 728 - 731 .

王巍 , 谷壬倩 , 彭力 , 等 . 基于无人机的物联网空基中继鲁棒优化 [J ] . 物联网学报 , 2022 , 6 ( 1 ): 101 - 112 .

WANG W , GU R Q , PENG L , et al . Robust optimization of air based relay for Internet of things based on UAV [J ] . Chinese Journal on Internet of Things , 2022 , 6 ( 1 ): 101 - 112 .

SHEN L F , WANG N , ZHANG D , et al . Energy-aware dynamic trajectory planning for UAV-enabled data collection in mMTC networks [J ] . IEEE Transactions on Green Communications and Networking , 2022 , 6 ( 4 ): 1957 - 1971 .

梅海波 , 杨鲲 , 范新宇 . 基于深度增强学习的无人机赋能雾无线电接入网络的能效优化 [J ] . 物联网学报 , 2021 , 5 ( 2 ): 48 - 59 .

MEI H B , YANG K , FAN X Y . Deep reinforcement learning to enhance the energy-efficient performance of UAV-enabled F-RAN [J ] . Chinese Journal on Internet of Things , 2021 , 5 ( 2 ): 48 - 59 .

SHEN L F , WANG N , ZHU Z Y , et al . UAV-enabled data collection over clustered machine-type communication networks: AEM modeling and trajectory planning [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 9 ): 10016 - 10032 .

HANIF S , ILYAS T , ZEESHAN M . Intrusion detection in IoT using artificial neural networks On UNSW-15 Dataset [C ] // Proceedings of the 2019 IEEE International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT and AI (HONET-ICT) . Piscataway : IEEE Press , 2019 : 152 - 156 .

JACKSON G , VALLES D . Dataset enlargement with generative adversarial neural networks [C ] // Proceedings of the 2024 IEEE World AI IoT Congress (AIIoT) . Piscataway : IEEE Press , 2024 : 0045 - 0051 .

KAUR N , GUPTA L . Enhancing IoT security in 6G environment with transparent AI: leveraging XGBoost, SHAP and LIME [C ] // Proceedings of the 2024 IEEE International Conference on Network Softwarization (NetSoft) . Piscataway : IEEE Press , 2024 : 180 - 184 .

ADIL M , AHMAD JAN M , LIU Y X , et al . A systematic survey: security threats to UAV-aided IoT applications, taxonomy, current challenges and requirements with future research directions [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 2 ): 1437 - 1455 .

ZHU Z Y , WANG N , HAO W M , et al . Robust beamforming designs in secure MIMO SWIPT IoT networks with a nonlinear channel model [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 3 ): 1702 - 1715 .

HUANG Y , LI Y J , CAI Z P . Security and privacy in metaverse: a comprehensive survey [J ] . Big Data Mining and Analytics , 2023 , 6 ( 2 ): 234 - 247 .

LI X W , ZHANG J Y , HAN C Z , et al . Reliability and security of CR-STAR-RIS-NOMA-assisted IoT networks [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 17 ): 27969 - 27980 .

GUO X H . Federated learning for data security and privacy protection [C ] // Proceedings of the 2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP) . Piscataway : IEEE Press , 2021 : 194 - 197 .

TIAN Y L , WANG S , XIONG J B , et al . Robust and privacy-preserving decentralized deep federated learning training: focusing on digital healthcare applications [J ] . IEEE/ACM Transactions on Computational Biology and Bioinformatics , 2024 , 21 ( 4 ): 890 - 901 .

NGUYEN D C , DING M , PATHIRANA P N , et al . Federated learning for Internet of Things: a comprehensive survey [J ] . IEEE Communications Surveys & Tutorials , 2021 , 23 ( 3 ): 1622 - 1658 .

WANG K I K , YE X , SAKURAI K . Federated learning with clustering-based participant selection for IoT applications [C ] // Proceedings of the 2022 IEEE International Conference on Big Data (Big Data) . Piscataway : IEEE Press , 2022 : 6830 - 6831 .

HE Z , WANG L , CAI Z . Clustered federated learning with adaptive local differential privacy on heterogeneous IoT data [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 1 ): 137 - 146 ..

MARNISSI O , EL HAMMOUTI H , HOUCINE BERGOU E . Client selection in federated learning based on gradients importance [J ] . ArXiv e-Prints , 2021 : arXiv: 2111.11204 .

RJOUB G , ABDEL WAHAB O , BENTAHAR J , et al . Trust-driven reinforcement selection strategy for federated learning on IoT devices [J ] . Computing , 2024 , 106 ( 4 ): 1273 - 1295 .

FU L , ZHANG H L , GAO G , et al . Client selection in federated learning: principles, challenges, and opportunities [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 24 ): 21811 - 21819 .

CHEN C , JIANG B H , LIU S L , et al . Efficient federated learning in resource-constrained edge intelligence networks using model compression [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 2 ): 2643 - 2655 .

KIM D , DOH I , CHAE K . Improved raft algorithm exploiting federated learning for private blockchain performance enhancement [C ] // Proceedings of the 2021 International Conference on Information Networking (ICOIN) . Piscataway : IEEE Press , 2021 : 828 - 832 .

DAUTOV R , HUSOM E J . Raft protocol for fault tolerance and self-recovery in federated learning [C ] // Proceedings of the 2024 IEEE/ACM 19th Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) . Piscataway : IEEE Press , 2024 : 110 - 121 .

LIU C , GUO S Y , GUO S , et al . LTSM: lightweight and trusted sharing mechanism of IoT data in smart city [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 7 ): 5080 - 5093 .

YAHATA Y , SUGIURA K , MATSUTANI H . A scalable secure fault tolerant aggregation for P2P federated learning [C ] // Proceedings of the 2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) . Piscataway : IEEE Press , 2024 : 222 - 231 .

XU X , HOU L , LI Y , et al . Weighted raft: An improved blockchain consensus mechanism for Internet of things application [C ] // Proceedings of the 2021 International Conference on Computer and Communications (ICCC) . Piscataway : IEEE Press , 2021 : 1520 - 1525 .

HOU L , XU X , ZHENG K , et al . An intelligent transaction migration scheme for raft-based private blockchain in Internet of things applications [J ] . IEEE Communications Letters , 2021 , 25 ( 8 ): 2753 - 2757 .

BUTTAR H M , AMAN W , RAHMAN M M U , et al . Countering active attacks on raft-based IoT blockchain networks [J ] . IEEE Sensors Journal , 2023 , 23 ( 13 ): 14691 - 14699 .

王光辉 , 白天水 , 丁爽 , 等 . 基于代理选举的高效异构联邦学习方法 [J ] . 计算机应用研究 , 2024 , 41 ( 3 ): 688 - 693 .

WANG G H , BAI T S , DING S , et al . Efficient and heterogeneous federated learning based on agent election [J ] . Application Research of Computers , 2024 , 41 ( 3 ): 688 - 693 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

车辆算力网络中异步鲁棒联邦学习方法研究

移动边缘计算中通信高效的联邦学习模型剪枝算法

联邦学习赋能6G网络综述

基于背包模型的联邦学习客户端选择方法

一种基于带宽分配的联邦学习激励机制