Fast Cars, Big Data - How Streaming Can Help Formula 1
summary
Shows a working pipeline that streams simulator ticks into Apache Kafka, stores raw events on a distributed file system and in a JSON NoSQL store, and runs real‑time aggregation with Apache Flink (average speed, 5s windows). Uses Apache Drill for ad hoc SQL on JSON. Targets real F1 scale: ~300 sensors per car and ~250 TB generated per race weekend (2014). Demo includes a live dashboard and a successful Anki toy‑car demo.
AI-written summary · about
chapters (10)
- 0:00Introduction to streaming in Formula 1
- 2:28Why data matters in motorsport
- 9:41Live demonstration setup
- 13:16Real-time dashboard walkthrough
- 16:16Architecture behind the demo
- 23:05Streaming technology deep dive
- 32:36Flexibility in data processing
- 35:55Stream processing with Flink
- 39:52Alternative demo with Anki cars
- 41:56Q&A and closing remarks
related talks
40mFast Cars, Big Data - How Streaming Can Help Formula 1 #bbuzz
25mFormula 1 telemetry processing using Kafka Streams
20mInnovating at speed
29mUse sports data to elevate fan engagement and performance
47mBuilding Modern Data Streaming Apps with Open Source
39mDeploying Fast Data Pipelines
27mStream, Store, Visualize: Fast-Track Real-Time Analytics the OSS Way
42mPrinciples and Patterns for Streaming Data Analysis