Osmotic Cloud-Edge Intelligence for IoT-Based Cyber-Physical Systems

Abstract

Artificial Intelligence (AI) in Cyber-Physical Systems allows machine learning inference on acquired data with ever greater accuracy, thanks to models trained with massive amounts of information generated by Internet of Things devices. Edge Intelligence is increasingly adopted to execute inference on data at the border of local networks, exploiting models trained in the Cloud. However, the training tasks on Edge nodes are not supported yet with flexible dynamic migration between Edge and Cloud. This paper proposes a Cloud-Edge AI microservice architecture, based on Osmotic Computing principles. Notable features include: (i) containerized architecture enabling training and inference on the Edge, Cloud, or both, exploiting computational resources opportunistically to reach the best prediction accuracy; and (ii) microservice encapsulation of each architectural module, allowing a direct mapping with Commercial-Off-The-Shelf (COTS) components. Grounding on the proposed architecture: (i) a prototype has been realized with commodity hardware leveraging open-source software technologies; and (ii) it has been then used in a small-scale intelligent manufacturing case study, carrying out experiments. The obtained results validate the feasibility and key benefits of the approach.

A Survey of AI Techniques in IoT Applications with Use Case Investigations in the Smart Environmental Monitoring and Analytics in Real-Time IoT Platform

“…Once the model is generated, it is sent back to the edge nodes. Following this concept, in [75], Loseto et al proposed edge intelligence components that allow edge devices to perform data training using local data to generate models for early prediction. Using data collected from multiple edge devices, the cloud performs more advanced data training to generate highly accurate models and sends them to the edge devices.…”

Integration of Digital Twin, Machine-Learning and Industry 4.0 Tools for Anomaly Detection: An Application to a Food Plant

“…The IoT is a network of physical objects embedded with sensors, software, and other technologies for the purpose of connecting and exchanging data with other devices and systems over the internet; it thus collects and shares data between smart devices to carry out data monitoring and control in cyber-physical systems (CPS). Artificial intelligence (AI) solutions applied to CPSs allow for machine learning (ML) inference on numerous data that can be acquired with ever-increasing accuracy, thanks to the possibility of training ML models with massive amounts of information generated by IoT devices [2]. With the introduction of ML techniques in the Industry 4.0 paradigm, each industrial field can take advantage of real-time monitoring and control of the production processes, thanks to the effective data analysis and prediction enabled by these techniques.…”