THE FASTEST CARS DESERVE
THE FASTEST CLOUD
FORMULA 1 is a battle between the world’s best drivers, but it’s also a battle of some of the world’s most innovative engineers. No other sport has been as dynamic in its evolution and embrace of new technology. While some of the tech goes to helping drivers, who are hitting speeds as high as 230 MPH, taking pit stops in under 2 seconds, and flying around corners with a force of 5G, much of it goes to enhance the experiences of its growing base of over a half a billion fans. This is why AWS is proud to be both the official cloud service and machine learning provider for FORMULA 1.
Here’s how it works:
Transforming
the series
Technology has always played a central role in the evolution of the sport, but serverless and machine learning are changing how F1 automates, collects, analyzes, and leverages data to make decisions.
Increasing action
on the track
F1 is taking the competition to the next level by altering some of the rules around car design. F1 simulates these changes using AWS High Performance Compute services to make sim cycles faster and more sophisticated.
Delivering deeper
insights
F1 uses Amazon SageMaker to build Machine Learning models that help fans better understand the split-second decisions made by a driver or pit crew that can dramatically affect the outcome.
Formula 1 works with AWS to Develop
Next Generation Race Car
The F1 Computational Fluid Dynamics project utilized over 12,000 hours of compute time to design the race car for the 2021 season. Watch F1 Chief Technical Engineer Rob Smedley’s re:Invent keynote on partnering with AWS to change the design and improve the fan experience. Visit the link below to read the press release about project.
AI Drives Racing into the
Next Generation
Watch the CNN interview with Ariel Kelman, VP of Marketing for AWS, Rob Smedley, F1 Chief Technical Engineer, and Dean Locke, F1 Director of Broadcasting, discussing how AI and big data solutions are ushering in a bold new era for FORMULA 1 Racing.
IT STARTS WITH
THE DATA
During a FORMULA 1 Grand Prix every car contains 120 sensors which generate 1.1M telemetry data points per second transmitted from the cars to the pits. This real-time data is combined with over 69 years of historical race data stored on S3 to inform fans and teams about the unparalleled track-side decision making.
MORE ACTION
ON THE TRACK
For FORMULA 1 cars, the downforce generated by their aerodynamics is the single largest performance differentiator, helping a car travel faster through corners. The current generation of cars suffer a loss of downforce when they are running in the wake of another car, and the ability to sustain close racing and overtaking is reduced. To reduce this downforce loss, F1 used AWS to look closely at how cars interact when racing together.
The Computational Fluid Dynamics (CFD) project tests the aerodynamics of cars while racing, carrying out detailed simulations that have resulted in the proposed car design for the 2021 racing season. The CFD project used over 1,150 compute cores to run transient simulations of over 550 million cells that model the impact of one car’s aerodynamic wake on another. Using AWS, and the scale of the cloud, FORMULA 1 was able to reduce the average simulation time by over 80 percent—from 60 hours down to 10. The project took six months to refine using Amazon Elastic Compute Cloud (Amazon EC2) c5n instances and delivered performance equivalent to that of a supercomputer costing millions of dollars. With the insights gained from these simulations, FORMULA 1 has been able to specify a car with only 10 percent downforce loss at the same 1 car length distance. The resulting car will feature a brand-new bodywork design and will run on 18-inch wheels with low profile tyres for the first time.
"This project with AWS was one of the most revolutionary in the history of Formula 1 aerodynamics. Nobody designs a car to come in second, but for this CFD project we were looking at how cars perform in the wake of another, as opposed to running in clean air.”
- Pat Symonds, Chief Technical Officer of FORMULA 1
"This project with AWS was one of the most revolutionary in the history of Formula 1 aerodynamics. Nobody designs a car to come in second, but for this CFD project we were looking at how cars perform in the wake of another, as opposed to running in clean air.”
- Pat Symonds, Chief Technical Officer of FORMULA 1
SHIFT THE FAN EXPERIENCE
INTO GEAR
By sourcing historical data and using it to teach Amazon SageMaker complex machine learning algorithms, F1 can predict race strategy outcomes with increasing accuracy for teams, cars, and drivers. These models are then able to predict future scenarios using refreshed realtime data as Grand Prix races unfold to deliver a rich and engaging fan experience.
Battle Forecast
Throughout F1 history, some of the most exciting racing action on track has come from driver ‘battles’ —when a chasing driver gets close enough to attempt an overtake. The resulting fight for position results in an unpredictable and sometimes dangerous combination of offensive and defensive driving action between the drivers involved. The Battle Forecast graphic analyses track history and projected driver pace to provide an insight into developing driver battles during the race that are not always obvious to the audience.
Pit Strategy Battle
Undercutting and overcutting are strategies used by F1 teams during close racing scenarios to gain a lead over a rival, with the margin between success and failure measured in tenths of a second. Pit Strategy Battle provides fans and commentators with real-time insight on the position of the two rival drivers, the predicted gap after their respective pit stops, and the percentage chance of an overtake, helping fans to assess how successful each driver’s strategy will be in real time and its potential outcome.
Tyre Performance
F1 teams are allowed a range of tyre compounds providing performance ranging from higher grip to longer lifespan. Tyre performance and degradation is a primary concern of the teams during a race and finding the perfect balance between lap time and tyre condition is a critical element of a race winning strategy. By analyzing timing and telemetry information and estimating lap time lost due to tyre power and tyre energies, Tyre Performance gives fans and commentators a better understanding of the current performance level.
Battle Forecast
Throughout F1 history, some of the most exciting racing action on track has come from driver ‘battles’ —when a chasing driver gets close enough to attempt an overtake. The resulting fight for position results in an unpredictable and sometimes dangerous combination of offensive and defensive driving action between the drivers involved. The Battle Forecast graphic analyses track history and projected driver pace to provide an insight into developing driver battles during the race that are not always obvious to the audience.
Pit Strategy Battle
Undercutting and overcutting are strategies used by F1 teams during close racing scenarios to gain a lead over a rival, with the margin between success and failure measured in tenths of a second. Pit Strategy Battle provides fans and commentators with real-time insight on the position of the two rival drivers, the predicted gap after their respective pit stops, and the percentage chance of an overtake, helping fans to assess how successful each driver’s strategy will be in real time and its potential outcome.
Products powering F1 Insights
Getting Started With Professional Services
In 2018 F1 engaged with the AWS Professional Services (ProServ) team, who has since delivered two models to support race graphics: Pit Stop Advantage in March 2019, and Battle Forecast in July 2019. F1 continues to innovate with the Professional Services team and Machine Learning Solutions Lab to accelerate development of F1 Insights by prototyping use cases and develop new proofs of concept. The ProServ team then helps F1 get models in to production and integrated into the F1 infrastructure.
