Daimler AG
Formula One switches from on-premise to machine learning on AWS
Formula One plans to use advanced analytics to improve the data it can show to motor racing fans
The Formula One Group (Formula 1) has signed up Amazon Web Services (AWS) as it moves most of its infrastructure from on-premise datacentres to the public cloud.
According to AWS, Formula 1 will use machine learning and data analytics services in the Amazon public cloud to accelerate its cloud transformation. Among the services being used is Amazon SageMaker, a fully managed machine learning service that enables developers and scientists to build and deploy machine learning models; Lambda, AWS’s event-driven serverless computing service; and AWS’s analytics service.
Using Amazon SageMaker, Formula 1’s data scientists are training deep learning models with 65 years of historical race data, stored in both Amazon DynamoDB and Amazon Glacier, said AWS. The tool enables the data scientists to obtain race performance statistics for making race predictions and give fans insight into the split-second decisions and strategies adopted by teams and drivers.
For example, AWS said Formula 1 data scientists can predict when the window of opportunity is opening and closing for teams to pit their cars for maximum advantage, as well as determine the best timing for changing tyres.
By streaming real-time race data to AWS using Amazon Kinesis, Formula 1 can capture and process key performance data for each car during every twist and turn of the F1 circuits. This data can then be processed using advanced machine learning in SageMaker.
By sharing these insights with fans through television broadcasts and digital platforms, Formula 1 is improving fans’ experience, said AWS, allowing them to dive deep into the inner workings of their favorite teams and drivers.
AWS said Formula 1 has also selected AWS Elemental Media Services to power its video asset workflows, enhancing the viewing experience for its 500 million fans worldwide.
Read more about SageMaker
- The latest service in AWS’s AI portfolio, Amazon SageMaker, is designed to simplify the deployment of new machine learning models, but still requires data science skills.
- SageMaker from AWS gives software developers a way to tackle AI and machine learning. But expert Torsten Volk said it will also require lots of experimenting.
Pete Samara, director of innovation and digital technology at Formula 1, said: “By leveraging Amazon SageMaker and AWS’s machine learning services, we are now able to deliver these powerful insights and predictions to fans in real time.
“We are also excited that the Formula 1 Motorsports division will run high-performance compute workloads in a scalable environment on AWS. This will significantly increase the number and quality of the simulations our aerodynamics team can run as we work to develop the new car design rules for Formula 1.”
