基于边缘计算的环境监测自适应联邦学习算法

蒋伟进; 韩裕清; 吴玉庭; 周为; 陈艺琳; 王海娟

doi:10.12263/DZXB.20230504

您当前的位置：

首页 >

文章列表页 >

基于边缘计算的环境监测自适应联邦学习算法

学术论文 | 更新时间：2025-12-08

- 基于边缘计算的环境监测自适应联邦学习算法
- Federated Learning Scheme for Environmental Monitoring Based on Edge Computing
- 电子学报 2023年51卷第11期页码：3061-3069
- 作者机构：
  
  1.湖南工商大学计算机学院,湖南长沙 410205
  2.武汉理工大学计算机与人工智能学院,湖北武汉 430070
  3.湘江实验室,湖南长沙 410205
  4.湖南工商大学前沿交叉学院,湖南长沙 410205
- 作者简介：
  
  [ "蒋伟进男，1964年7月出生于湖南省益阳市.现为湖南工商大学计算机学院二级教授、硕士生导师.主要研究方向为联邦学习、群智感知、边缘计算、社会计算. E-mail: jwjnudt@163.com" ]
  [ "韩裕清清（通讯作者）男，2000 年 11 月出生于湖南省长沙市 . 现为湖南工商大学计算机学院硕士研究生. 主要研究方向为联邦学习、边缘计算、群智感知.E-mail: 897735614@qq.com" ]
  [ "吴玉庭女，1998年4月出生于湖南省益阳市. 现为湖南工商大学计算机学院硕士研究生.主要研究方向为联邦学习、群智感知. E-mail: 1321224262@qq.com" ]
  [ "周为男，2000年5月出生于湖南省益阳市. 现为湖南工商大学计算机学院硕士研究生.主要研究方向为联邦学习、群智感知. E-mail: 1216330671@qq.com" ]
  [ "陈艺琳女，2000年9月出生于河南省许昌市. 现为湖南工商大学计算机学院硕士研究生.主要研究方向为联邦学习、信息安全. E-mail: 1986746095@qq.com" ]
  [ "王海娟女，2000年5月出生于江西省九江市. 现为湖南工商大学前沿交叉学院硕士研究生.主要研究方向为联邦学习、群智感知. E-mail: 2502560411@qq.com" ]
- 基金信息：
  
  国家自然科学基金(61772196;72088101);湖南省自然科学基金(2020JJ4249)
- DOI：10.12263/DZXB.20230504
  中图分类号： TP301
- 收稿：2023-06-05，
  
  修回：2023-08-16，
  
  纸质出版：2023-11-25
- 稿件说明：
移动端阅览
蒋伟进,韩裕清,吴玉庭等.基于边缘计算的环境监测自适应联邦学习算法[J].电子学报,2023,51(11):3061-3069.

JIANG Wei-jin,HAN Yu-qing,WU Yu-ting,et al.Federated Learning Scheme for Environmental Monitoring Based on Edge Computing[J].ACTA ELECTRONICA SINICA,2023,51(11):3061-3069.
蒋伟进,韩裕清,吴玉庭等.基于边缘计算的环境监测自适应联邦学习算法[J].电子学报,2023,51(11):3061-3069. DOI： 10.12263/DZXB.20230504.

JIANG Wei-jin,HAN Yu-qing,WU Yu-ting,et al.Federated Learning Scheme for Environmental Monitoring Based on Edge Computing[J].ACTA ELECTRONICA SINICA,2023,51(11):3061-3069. DOI： 10.12263/DZXB.20230504.

摘要

针对环境监测领域边缘设备资源不平衡、通信延迟以及模型质量不高的问题，本文提出一种基于边缘计算的环境监测自适应联邦学习算法.该算法旨在利用边缘设备进行数据处理，并根据各个设备的资源限制调整全局模型的聚合频率，以更好地适应不同的监测环境.通过考虑边缘设备之间的资源差异，算法采用了动态优化迭代频率的策略，以提升模型的训练效果.与传统的固定迭代频率相比，该算法的调整策略更加灵活，能够更好地适应不同的数据分布和参与方特征.通过大量实验评估，并利用与同类算法CNN-FL（Convolutional Neural Networks-Federated Learning），FedAvg（Federated Averaging）和HFEL（Hierarchical Federated Edge Learning）的比较，本文提出的算法在算法性能和经济成本方面具有显著优势，这种算法为环境监测提供了一种高效、安全和可扩展的数据分析和模型建立方法，有助于推动环境监测能力的提升.

Abstract

Aiming at the problems of unbalanced edge device resources

communication delay and low model quality in the field of environmental monitoring

this paper proposes an adaptive federated learning algorithm for environmental monitoring based on edge computing. This algorithm aims to use edge devices for data processing

and according to each the resource limitation of the device adjusts the aggregation frequency of the global model to better adapt to different monitoring environments. By considering the resource differences between edge devices

the algorithm adopts a strategy of dynamically optimizing the iteration frequency to improve the training effect of the model. Compared with the traditional fixed iteration frequency

the adjustment strategy of this algorithm is more flexible and can better adapt to different data distribution and participant characteristics. Through a large number of experimental evaluations

and using the same algorithm convolutional neural networks-federated learning (CNN-FL)

federated averaging (FedAvg) and hierarchical federated edge learning (HFEL)

the algorithm proposed in this paper has significant advantages in algorithm performance and economic cost. This algorithm provides an efficient

safe and reliable method for environmental monitoring. Expanded approach to data analysis and modeling to help drive improvements in environmental monitoring capabilities.

关键词

Keywords

references

MONTRUCCHIO B , GIUSTO E , VAKILI M G , et al . A densely-deployed, high sampling rate, open-source air pollution monitoring WSN [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 12 ): 15786 - 15799 .

ZHU B T , BEDEER E , NGUYEN H H , et al . UAV trajectory planning for AoI-minimal data collection in UAV-aided IoT networks by transformer [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 2 ): 1343 - 1358 .

SABARI M , ASWINTH P , KARTHIK T , et al . Water quality monitoring system based on IoT [C ] // 2020 5th International Conference on Devices, Circuits and Systems (ICDCS) . Piscataway : IEEE , 2020 : 279 - 282 .

刘艳 , 王田 , 彭绍亮 , 等 . 基于边缘的联邦学习模型清洗和设备聚类方法 [J ] . 计算机学报 , 2021 , 44 ( 12 ): 2515 - 2528 .

LIU Y , WANG T , PENG S L , et al . Edge-based model cleaning and device clustering in federated learning [J ] . Chinese Journal of Computers , 2021 , 44 ( 12 ): 2515 - 2528 . (in Chinese)

LIU Y , HUANG A B , LUO Y , et al . FedVision: An online visual object detection platform powered by federated learning [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 8 ): 13172 - 13179 .

YANG Z H , CHEN M Z , SAAD W , et al . Energy efficient federated learning over wireless communication networks [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 3 ): 1935 - 1949 .

LIU Y , NIE J T , LI X D , et al . Federated learning in the sky: Aerial-ground air quality sensing framework with UAV swarms [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 12 ): 9827 - 9837 .

DEY S , PAL S . Federated learning-based air quality prediction for smart cities using BGRU model [C ] // Proceedings of the 28th Annual International Conference on Mobile Computing and Networking . New York : ACM , 2022 : 871 - 873 .

T M , MAKKITHAYA K , G N V . A federated learning-based crop yield prediction for agricultural production risk management [C ] // 2022 IEEE Delhi Section Conference (DELCON) . Piscataway : IEEE , 2022 : 1 - 7 .

SUN T , TANG K , LI D S . Gradient descent learning with floats [J ] . IEEE Transactions on Cybernetics , 2022 , 52 ( 3 ): 1763 - 1771 .

ABBAS N , ZHANG Y , TAHERKORDI A , et al . Mobile edge computing: A survey [J ] . IEEE Internet of Things Journal , 2018 , 5 ( 1 ): 450 - 465 .

MILLS J , HU J , MIN G Y . Communication-efficient federated learning for wireless edge intelligence in IoT [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 7 ): 5986 - 5994 .

SULIMAN M , LEITH D J . Gradient information from google GBoard NWP LSTM is sufficient to reconstruct words typed [C ] // 2022 Cyber Research Conference - Ireland (Cyber-RCI) . Piscataway : IEEE , 2023 : 1 - 4 .

YANG M M , TJUAWINATA I , LAM K Y . K-means clustering with local dχ-privacy for privacy-preserving data analysis [J ] . IEEE Transactions on Information Forensics and Security , 2022 , 17 : 2524 - 2537 .

MAO Y Y , YOU C S , ZHANG J , et al . A survey on mobile edge computing: The communication perspective [J ] . IEEE Communications Surveys & Tutorials , 2017 , 19 ( 4 ): 2322 - 2358 .

JIE T . Research on key technologies of advanced electronic measurement sensors based on computer Internet of Things [C ] // 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT) . Piscataway : IEEE , 2022 : 856 - 860 .

KIRTI , RAJPAL N . Black rot disease detection in grape plant (vitis vinifera) using colour based segmentation & machine learning [C ] // 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN) . Piscataway : IEEE , 2021 : 976 - 979 .

WEN W L , CHEN Z H , YANG H H , et al . Joint scheduling and resource allocation for hierarchical federated edge learning [J ] . IEEE Transactions on Wireless Communications , 2022 , 21 ( 8 ): 5857 - 5872 .

SALIM M M , PARK J H . Federated learning-based secure electronic health record sharing scheme in medical informatics [J ] . IEEE Journal of Biomedical and Health Informatics , 2022 , 27 ( 2 ): 617 - 624 .

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

基于自适应联邦学习的环境监测群智感知算法

基于轻量自蒸馏的低成本联邦学习

边缘计算环境下基于PUF的多接收者匿名签密方案

基于双层联邦学习的高动态车联网业务边缘协作计算机制