Overview

As member of Akraino's Kubernetes-Native Infrastructure family of blueprints, the Industrial Edge (IE) blueprint leverages the best-practices and tools from the Kubernetes community to declaratively manage edge computing stacks (i.e. all infrastructure, clusters, and services) at scale and with a consistent, uniform user experience.

The Industrial Edge blueprint addresses a common use case in manufacturing which is "predictive maintenance", the detection of anomalies in sensor data coming from production line servers to be able to schedule maintenance and avoid costly downtimes. Anomaly detection is based on machine learning inference on streaming sensor data.

The 3-node, highly-available clusters produced by this blueprint are manageble via a central management hub running Open Cluster Managemer and using GitOps principles.

The management hub cluster also deploys OpenDataHub that allows streaming data from factory edge clusters to be stored in a data lake for re-training of machine learning models. OpenDataHub also deploys Jupyter Notebooks for data scientists to analyse data and work on models. Updated models can be distributed out to the factory via the same GitOps mechanisms used also for updates of the clusters and their workloads.

Documentation

User Documentation for KNI Blueprints

KNI IE Architecture

KNI IE Installation Guide

KNI IE Test document

Project Team

Project Templates

Use Case Template

Blueprint Template