AIDA—A holistic AI-driven networking and processing framework for industrial IoT applications

• DOI: 10.1016/j.iot.2023.100805
• Publication Date: 2023-05-06T15:38:08Z
• Authors: Hamza Chahed; Muhammad Usman; Ayan Chatterjee; Firas Bayram; Rajat Chaudhary; Anna Brunstrom; Javid Taheri; Bestoun S. Ahmed; Andreas Kassler
• Keywords: Microservices; Downtime

Industry 4.0 is characterized by digitalized production facilities, where a large volume of sensors collect vast amount data that used to increase the sustainability e.g. optimizing process parameters, reducing machine downtime and material waste, like. However, making intelligent data-driven decisions under timeliness constraints requires integration time-sensitive networks with reliable ingestion processing infrastructure plug-in support Machine Learning (ML) pipelines. such difficult due lack frameworks flexibly integrate program networking computing infrastructures, while allowing ML pipelines ingest collected make trustworthy in real time. In this paper, we present AIDA - novel holistic AI-driven network framework for real-time industrial IoT applications. manages configures Time-Sensitive (TSN) enable into an observable AI-powered edge/cloud continuum. Pluggable components timely various applications itself are intrinsic part AIDA. We introduce architecture, demonstrate building blocks our illustrate it two use cases.