Abstract: The convergence of the Industrial Internet of Things (IIoT) and Artificial Intelligence (AI) has given rise to Industry 4.0, creating a wealth of opportunities for manufacturing companies. Nevertheless, the adoption of this paradigm shift, particularly in smart factories and production, is still in its early stages and faces several obstacles, such as substandard data quality and fragmentation, resulting in limited insight driven IIoT innovation. To overcome these challenges, this article highlights a decentralized architecture that utilizes emerging multi-party technologies, privacy-enhancing techniques like Federated Learning, and AI approaches. The proposed approach strives to establish a cross-company collaboration platform and a federated data space that addresses the fragmented data landscape. Federated Learning is one way to enable the sharing of confidential data generated from various IIoT devices. However, traditional Federated Learning raises privacy concerns. This review introduces the basics of FL, describing its underlying implementation of technologies, advantages and disadvantages, and recommendations, along with privacy-preserving methods. Most importantly, this work contributes to comprehending a broad range of FL current applications and future trends in technology and markets today.
Keywords: Federated Learning, Cybersecurity, IoT, Edge Computing.
Cite:
Deepak Kumar, Priyanka Pramod Pawar , Hari Gonaygunta , Shoumya Singh, "Impact of Federated Learning on Industrial IoT - A Review", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 1, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13105.
|
DOI:
10.17148/IJARCCE.2024.13105
