Control

Control provides cellular telemetry solutions in motorsport that ensure data moves seamlessly from in-car cellular devices to race engineers located worldwide to monitor vehicle performance.

Startup of the Year
2022
Startup of the Year
2022
Startup of the Year
2022
Startup of the Year
2022

Control’s solution allows the company to update each car’s connectivity automatically.

Control improved race performance with a streaming architecture and ML models that connected in-car devices and cloud transformations in real-time.

Technologies Used:
  • Apache Kafka®
  • Quix

What problem was the nominee organization looking to solve with Data Streaming Technology?

When an in-car device arrived at a new racetrack, its three modems automatically connected to the first available network, not the best available network. This degraded race performance up to 23% compared to optimal conditions. Control engineers made manual adjustments to correct this discrepancy, but doing so required time-intensive calculations at the beginning of and throughout each race. Devices were missed, and decisions were made on historic data rather than the data at hand. 

How did they solve the problem?
  • Connect Quix to Control’s existing Azure Event Hub infrastructure to receive data streams
  • Transform raw messages into a structured data schema with standard business semantics
  • Contextualize data, so each car is associated with just one data stream
  • Store high-quality data from actual vehicles and train ML models on that data
  • Deploy the models into a stream processing pipeline to rank the best connectivity
  • Automatically update a configuration table in real time to optimize connectivity"

What was the positive outcome?

Control’s solution allows the company to update each car’s connectivity automatically. This removed a massive operational burden and eliminates the risk that a customer would needlessly suffer up to 23% performance degradation. The data pipeline is now resilient because it replicates and shards the data and the processing. With Quix, Control’s small team stood up, trained, tested, and deployed 82 ML models in just two weeks. Control is now confident that its product performs consistently.

Additional Links: