Zurück

Real Time Streaming Analytics with 100.000 Connected Cars using MQTT, Kafka, Kubernetes and TensorFlow

This session discusses uses cases leveraging Apache Kafka open source ecosystem as streaming platform to process IoT data. See architectural alternatives and a live demo of how devices connect to Kafka via MQTT. Learn how to analyze the IoT data either natively on Kafka with Kafka Streams/KSQL, or on an external big data cluster like Spark, Flink or Elastic leveraging Kafka Connect, and how to leverage TensorFlow for Machine Learning. A live demo shows how to build a cloud native IoT infrastructure on Kubernetes to connect and process streaming data in real time from 100.000 cars to do predictive maintenance at scale in real time.

Vorkenntnisse

Experience with some open source frameworks or products (Machine Learning, Messaging, Integration, Stream Processing) helpful but not required

Lernziele

See different end-to-end use cases where you integrate IoT devices with enterprise IT using open source technologies and standards
Understand the benefits and challenges of MQTT, and how to realize even extreme scale scenarios
See how the Apache Kafka enables end-to-end real time integration processing from IoT data to various backend applications

Speaker

Kai Waehner is Field CTO at Confluent. He works with customers across the globe and with internal teams like engineering and marketing. Kai’s main area of expertise lies within the fields of Big Data Analytics, Machine Learning, Hybrid Cloud Architectures, Event Stream Processing, and Internet of Things.

Jetzt Tickets sichern

building-IoT-Newsletter

Sie möchten über die building IoT
auf dem Laufenden gehalten werden?

Anmelden