Stable federated learning method for low-altitude IoT networks based on election strategy

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, al...

Full description

Saved in:
Bibliographic Details
Main Authors: SHEN Lingfeng, WANG Guanghui, BAI Tianshui, ZHU Zhengyu, ZHANG Qiankun
Format: Article
Language:zho
Published: China InfoCom Media Group 2024-09-01
Series:物联网学报
Subjects:
Online Access:http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00415/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850034584396234752
author SHEN Lingfeng
WANG Guanghui
BAI Tianshui
ZHU Zhengyu
ZHANG Qiankun
author_facet SHEN Lingfeng
WANG Guanghui
BAI Tianshui
ZHU Zhengyu
ZHANG Qiankun
author_sort SHEN Lingfeng
collection DOAJ
description 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.
format Article
id doaj-art-c137945727d845f8982f2faa752296fe
institution DOAJ
issn 2096-3750
language zho
publishDate 2024-09-01
publisher China InfoCom Media Group
record_format Article
series 物联网学报
spelling doaj-art-c137945727d845f8982f2faa752296fe2025-08-20T02:57:46ZzhoChina InfoCom Media Group物联网学报2096-37502024-09-018556577121100Stable federated learning method for low-altitude IoT networks based on election strategySHEN LingfengWANG GuanghuiBAI TianshuiZHU ZhengyuZHANG QiankunThe 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.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00415/low-altitude IoTfederated learningdevice election strategystabilitytraining efficiency
spellingShingle SHEN Lingfeng
WANG Guanghui
BAI Tianshui
ZHU Zhengyu
ZHANG Qiankun
Stable federated learning method for low-altitude IoT networks based on election strategy
物联网学报
low-altitude IoT
federated learning
device election strategy
stability
training efficiency
title Stable federated learning method for low-altitude IoT networks based on election strategy
title_full Stable federated learning method for low-altitude IoT networks based on election strategy
title_fullStr Stable federated learning method for low-altitude IoT networks based on election strategy
title_full_unstemmed Stable federated learning method for low-altitude IoT networks based on election strategy
title_short Stable federated learning method for low-altitude IoT networks based on election strategy
title_sort stable federated learning method for low altitude iot networks based on election strategy
topic low-altitude IoT
federated learning
device election strategy
stability
training efficiency
url http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00415/
work_keys_str_mv AT shenlingfeng stablefederatedlearningmethodforlowaltitudeiotnetworksbasedonelectionstrategy
AT wangguanghui stablefederatedlearningmethodforlowaltitudeiotnetworksbasedonelectionstrategy
AT baitianshui stablefederatedlearningmethodforlowaltitudeiotnetworksbasedonelectionstrategy
AT zhuzhengyu stablefederatedlearningmethodforlowaltitudeiotnetworksbasedonelectionstrategy
AT zhangqiankun stablefederatedlearningmethodforlowaltitudeiotnetworksbasedonelectionstrategy