An effective Federated Learning system for Industrial IoT data streaming

被引:1
作者
Wu, Yi [1 ]
Yang, Hongxu [1 ]
Wang, Xidong [1 ]
Yu, Hongjun [2 ]
El Saddik, Abdulmotaleb [3 ,4 ]
Hossain, M. Shamim [5 ]
机构
[1] Heilongjiang Univ, Sch Data Sci & Technol, Harbin, Peoples R China
[2] Heilongjiang Prov Cyberspace Res Ctr, Harbin, Peoples R China
[3] Univ Ottawa, Sch Elect Engn & Comp Sci EECS, Ottawa, ON, Canada
[4] Mohamed Bin Zayed Univ Artificial Intelligence, Abu Dhabi, U Arab Emirates
[5] King Saud Univ, Coll Comp & Informat Sci, Dept Software Engn, Riyadh 12372, Saudi Arabia
关键词
IIoT; Federated Learning; Streaming data; Pairwise similarity; INTERNET; THINGS;
D O I
10.1016/j.aej.2024.07.040
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Due to its outstanding privacy-related characteristics, Federated Learning (FL) has recently become a popular solution for the IIoT's data privacy and scalability issues. However, more research is needed to determine how unique streaming data in IIoT Settings affects FL-enabled IIoT architectures, with unique streaming data affecting accuracy and reducing convergence performance. To achieve this goal, this paper explains the streaming data learning problem in an IIoT framework enabled by FL. Afterward, it outlines two unique issues relevant to this situation: convergence and the catastrophic forgetting that occurs throughout training. This article presents FedStream, a practical FL framework for IIoT streaming data applications, considering these challenges. In particular, we develop a straightforward and effective pairwise similarity-based streaming data replacement training method that systematically replaces original data samples with ones that show high similarity during the iterative training process. This not only improves the accuracy but also reduces the convergence process and catastrophic forgetting problem. Comprehensive case studies support the effectiveness of the proposed method. Finally, the article recommends potential research areas, encouraging academics and industry professionals to explore these emerging topics further.
引用
收藏
页码:414 / 422
页数:9
相关论文
共 46 条
[1]   Federated Learning-Assisted Distributed Intrusion Detection Using Mesh Satellite Nets for Autonomous Vehicle Protection [J].
Al-Hawawreh, Muna ;
Hossain, M. Shamim .
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (01) :854-862
[2]   The Internet of Things: A survey [J].
Atzori, Luigi ;
Iera, Antonio ;
Morabito, Giacomo .
COMPUTER NETWORKS, 2010, 54 (15) :2787-2805
[3]   An overview of the Internet of Things for people with disabilities [J].
Carmen Domingo, Mari .
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2012, 35 (02) :584-596
[4]  
Casado FE, 2021, Arxiv, DOI arXiv:2006.07129
[5]   End-to-End Incremental Learning [J].
Castro, Francisco M. ;
Marin-Jimenez, Manuel J. ;
Guil, Nicolas ;
Schmid, Cordelia ;
Alahari, Karteek .
COMPUTER VISION - ECCV 2018, PT XII, 2018, 11216 :241-257
[6]   Asynchronous Online Federated Learning for Edge Devices with Non-IID Data [J].
Chen, Yujing ;
Ning, Yue ;
Slawski, Martin ;
Rangwala, Huzefa .
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, :15-24
[7]  
Evensen M.N., 2021, Effective Cyber Security Strategies for IIoT Industrial IoT in the industry sector: Trust and Scalability
[8]  
Gallardo J, 2021, Arxiv, DOI [arXiv:2103.14010, 10.48550/arXiv.2103.14010]
[9]  
Gupta G, 2020, Adv Neural Inf Process Syst, V33, P11588
[10]  
Gutmann M., 2010, P 13 INT C ART INT S, V9, P297, DOI DOI 10.1145/3292500.3330651