The ML-based analytics can leverage the Kafka as an event server for various types of events, as depicted in the preceding diagram. The ML-based analytics can load the respective model coefficients from the registry and provide the predictions. After processing the events, analytics can publish the results (predictions) to Kafka, which can then be streamed to the clients. Likewise, the analytics can also publish the newly generated models to the registry.
Step 3
Get Industrial Internet Application Development now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.