Fusion of Federated Learning and Industrial Internet of Things: A survey

被引:107
作者
Boobalan, Parimala [1 ]
Ramu, Swarna Priya [1 ]
Quoc-Viet Pham [2 ]
Dev, Kapal [3 ]
Pandya, Sharnil [4 ]
Maddikunta, Praveen Kumar Reddy [1 ]
Gadekallu, Thippa Reddy [1 ]
Thien Huynh-The [5 ]
机构
[1] Vellore Inst Technol, Sch Informat Technol & Engn, Vellore, Tamil Nadu, India
[2] Pusan Natl Univ, Korean Southeast Ctr Ind Revolut Leader Educ 4, Busan, South Korea
[3] Univ Johannesburg, Dept Inst Intelligent Syst, Johannesburg, South Africa
[4] Symbiosis Int Deemed Univ, Symbiosis Inst Technol, Pune, Maharashtra, India
[5] Kumoh Natl Inst Technol, ICT Convergence Res Ctr, Gyeongsangbuk Do 39177, South Korea
基金
新加坡国家研究基金会;
关键词
Data storage; IIoT; Federated Learning; Data privacy; Data sharing; Resource management; INTELLIGENT CONTROL; ACCESS-CONTROL; DIGITAL TWINS; PRIVACY; BLOCKCHAIN; EFFICIENT; IOT; NETWORKING; MANAGEMENT; SECURITY;
D O I
10.1016/j.comnet.2022.109048
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Industrial Internet of Things (IIoT) lays a new paradigm for the concept of Industry 4.0 and paves an insight for new industrial era. Nowadays smart machines and smart factories use machine learning/deep learning based models for incurring intelligence. However, storing and communicating the data to the cloud and end device leads to issues in preserving privacy. In order to address this issue, Federated Learning (FL) technology is implemented in IIoT by the researchers nowadays to provide safe, accurate, robust and unbiased models. Integrating FL in IIoT ensures that no local sensitive data is exchanged, as the distribution of learning models over the edge devices has become more common with FL. Therefore, only the encrypted notifications and parameters are communicated to the central server. In this paper, we provide a thorough overview on integrating FL with IIoT in terms of privacy, resource and data management. The survey starts by articulating IIoT characteristics and fundamentals of distributed machine learning and FL. The motivation behind integrating IIoT and FL for achieving data privacy preservation and on-device learning are summarized. Then we discuss the potential of using machine learning (ML), deep learning (DL) and blockchain techniques for FL in secure IIoT. Further we analyze and summarize several ways to handle the heterogeneous and huge data. Comprehensive background on data and resource management are then presented, followed by applications of IIoT with FL in automotive, robotics, agriculture, energy, and healthcare industries. Finally, we shed light on challenges, some possible solutions and potential directions for future research.
引用
收藏
页数:20
相关论文
共 171 条
[1]  
Abad MSH, 2020, INT CONF ACOUST SPEE, P8866, DOI [10.1109/ICASSP40776.2020.9054634, 10.1109/icassp40776.2020.9054634]
[2]   Data Management for the Internet of Things: Design Primitives and Solution [J].
Abu-Elkheir, Mervat ;
Hayajneh, Mohammad ;
Abu Ali, Najah .
SENSORS, 2013, 13 (11) :15582-15612
[3]  
Agrawal S, 2021, Arxiv, DOI [arXiv:2106.09527, DOI 10.48550/ARXIV.2106.09527]
[4]   Federated Learning for Cybersecurity: Concepts, Challenges, and Future Directions [J].
Alazab, Mamoun ;
Priya, Swarna R. M. ;
Parimala, M. ;
Maddikunta, Praveen Kumar Reddy ;
Gadekallu, Thippa Reddy ;
Quoc-Viet Pham .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (05) :3501-3509
[5]  
Khowaja SA, 2022, Arxiv, DOI arXiv:2107.12806
[6]  
[Anonymous], 2013, NEXT GENERATION WIRE
[7]  
Antunes R.S., 2022, ACM T INTEL SYST TEC
[8]   A Trustworthy Privacy Preserving Framework for Machine Learning in Industrial IoT Systems [J].
Arachchige, Pathum Chamikara Mahawaga ;
Bertok, Peter ;
Khalil, Ibrahim ;
Liu, Dongxi ;
Camtepe, Seyit ;
Atiquzzaman, Mohammed .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (09) :6092-6102
[9]  
Babayigit B, 2019, 2019 11TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONICS ENGINEERING (ELECO 2019), P890, DOI [10.23919/ELECO47770.2019.8990553, 10.23919/eleco47770.2019.8990553]
[10]  
Bagdasaryan E, 2020, PR MACH LEARN RES, V108, P2938