How Cloud Data-Crunching Power Accelerates the F1 Racing Experience

Today’s cars resemble rolling computers. That’s especially true of Formula 1 race cars, which push the envelope on technology as well as speed.

F1 teams rely on partnerships with technology providers, leveraging high-performance computing, machine learning and edge computing to gain an edge on the track. These relationships are also valuable to service providers, showcasing cutting-edge uses for their data center technologies.

F1 and its cloud-powered racers will be showcased this weekend at the 2021 United States Grand Prix at the Circuit of the Americas in Austin, Texas. Seven-time world champion Lewis Hamilton of Mercedes-AMG Petronas has won five times in Austin, but enters this week’s race trailing rival Max Verstappen of Red Bull by just six points in one of the most intense championship battles in years.

It’s hard to overstate the role technology plays in F1 racing. Every F1 car contains 300 sensors which generate 1.1 million telemetry data points per second transmitted from the cars to the pits. During each race weekend 160 terabytes of data is sent between the remote race circuit and the F1 Media and Technology Center in Biggin Hill, England.

“It’s been a bit of an arms race over the last decade,” said Michael Taylor, IT director for the Mercedes-AMG Petronas Formula One Team, which works with HPE on leveraging edge computing to improve racing performance. “With the major advancements in processing capability, chips, and memory, all teams have made significant investments in technology to improve their chances on the track.”

“Formula One teams have always been pioneers in analyzing data for a competitive advantage, especially when milliseconds mean the difference between pole position and starting somewhere in the middle of the pack,” said Otmar Szafnauer, chief executive officer and team principal at Aston Martin Cognizant Formula One.

F1 and Amazon Web Services

At the heart of the Formula One Group’s technology is a deep relationship with Amazon Web Services, which provides cloud horsepower for everything from computer-aided design for cars to an astonishing suite of data analytics and visualizations for F1 fans.

The car design for the 2021 season was developed using a Computational Fluid Dynamics (CFD) project to simulate the aerodynamics of cars while racing, using 1,150 compute cores to run detailed simulations, and crunching more than 550 million data points that model the impact of one car’s aerodynamic wake on another. The project ran for six months using Amazon Elastic Compute Cloud (Amazon EC2) c5n instances and delivered performance equivalent to that of a supercomputer for a small fraction of the cost.

“This project with AWS was one of the most revolutionary in the history of Formula 1 aerodynamics,” said Pat Symonds, Chief Technical Officer of Formula 1. “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. We have been able to use AWS technologies to understand the incredible aerodynamic complexities associated with multi-car simulations.”

F1 is also using cloud computing to bring fans inside the racing experience in news ways through F1 Insights, which uses a suite of AWS services to analyze real-time data feeds – including data from sensors along with video from on-board cameras and audio from team radio – and analyze them for live broadcasts around the globe. These insights help fans understand the split-second decisions and race strategies made by drivers or teams that can dramatically affect a race outcome.

“Our work with F1 demonstrates how advanced stats can elevate the fan experience by revealing the tactics and strategies behind even the most seemingly straightforward elements of a race,” said Darren Mowry, director of business development at AWS EMEA.

This real-time data is combined with over 70 years of historical race data stored on Amazon S3. A key step was migrating Formula 1’s massive library of 70 years of images, audio and video into the cloud. The AWS Media2Cloud service enabled F1 to transfer 150,000 hours of content from a tape archive into the AWS Cloud, allowing the assets to be indexed and tagged to provide historic insights for race analysis. This 6-minute video from AWS provides an overview, as well as a look at some of the IT hardware and workstations powering F1’s tech infrastructure.

In addition to F1’s corporate technology relationships, each of the F1 racing teams works closely with technology partners on everything from on-track performance to fan experiences (including future plans for virtual reality experiences) and eSports offerings for gamers. Here’s a look at the leading teams and their technology.

Mercedes-AMG Petronas

Mercedes is on track to win its eighth consecutive constructor’s championship. It helps to have the world’s most successful driver in Hamilton, but Mercedes also cites the importance of data-driven analytics through its partnership with HPE.

“In F1, we use data on our relentless search for performance, across all functions of the team – both at the track and at the factory,” said Toto Wolff, Team Principal & CEO of Mercedes-AMG Petronas Motorsport. “With the support of HPE we can better process and analyze that data, enabling our team members to do what they do best – from the early stages of conceiving a competitive car to the final moment of the car setup on a race weekend.”

HPE says it helps Mercedes gain an “edge” by using high-performance computing, analytics, and sensor technologies to crunch millions of data points and examine thousands of race scenarios, spanning everything from ideal pitstop times to tire selection to develop a strategic playbook for Mercedes and its drivers.

Red Bull Honda

Red Bull Honda Racing is having its best season in many years, currently running second in the constructor standings while Verstappen challenges for the driver’s championship. On the tech side, Red Bull works with Oracle Cloud Infrastructure (OCI) as its IT infrastructure provider. Team principal Christian Horner calls it “a hugely significant partnership.”

“Red Bull Racing Honda requires a cloud infrastructure platform with the highest levels of performance, scalability, and security,” said Horner. “Oracle Cloud Infrastructure brings unique capabilities enabling Red Bull to expand its use of data science and analytics, so it can accommodate the growing and diversifying engineering work undertaken on the Red Bull Technology Campus.”

The Red Bull campus in Milton Keynes, UK includes an AT&T Operations Room for performance engineers and race strategists, as well as an on-site data center named for driver Sebastian Vettel (now at Aston Martin), who won four world championships for Red Bull and was focused on data and performance.

McLaren

McLaren Racing, which currently stands third in the constructor standings, has long been a pioneer in using computers and data analysis in motor sports. In 1975 it became the first team to use telemetry, using sensors to capture performance data in the team’s IndyCar vehicles. It subsequently applied these techniques in Formula 1, including the first use of “burst” telemetry using radio signals to send in-race data from the car to the pits.

McLaren now works with Dell Technologies, which provides HPC horsepower that helps McLaren study, test and prototype aerodynamic changes to its car.

“We use HPC to conduct complex computational fluid dynamics (CFD) studies on the airflows around the digital twin of a proposed part before deciding whether to test it with rapid prototyping with 3D printers ready for wind-tunnel testing,” said Edward  Green, Principal Digital Architect for McLaren Racing, in a blog post. “In other words, we have the ability to test a part under widely variable conditions before it actually exists, which saves valuable time and expense.”

Dell HPC also supports McLaren Applied Technologies, which creates products for a variety of industries using insights that initiate within the racing operations.

McLaren also works with Splunk, which specializes in analytics using unstructured data (not in a database). Splunk’s Data-to-Everything Platform allows McLaren Group to capture unstructured data from across its infrastructure, network and server environments.

Ferrari

Scuderia Ferrari teams with AWS to access advanced analytics, machine learning and database capabilities to optimize its car design and performance. In announcing the partnership in June, the companies said Ferrari can run thousands of simulations concurrently, gaining insights faster than possible running simulations in an on-premises environment.

“Throughout our storied history, Ferrari has had racing and innovation at our core, and now we look forward to applying AWS machine learning, advanced analytics, and high-performance computing across the company to deliver deeper insights and even more powerful cars,” said Mattia Binotto, Principal of Scuderia Ferrari.

Ferrari also plans to build virtual and augmented reality experiences on AWS that bring fans into the garage to interact with drivers and team personnel.

Alpine Renault

Alpine Renault recently expanded its relationship with KX Insights, which provides a real-time streaming analytics platform running on the Microsoft Azure Cloud. KX Insights provides a single point of access to data across an entire organization, taking advantage of hybrid cloud architecture.

“With billions of data points being captured at the track and at the factory, it is critical to have a cloud infrastructure that is agile and can enable tools such as KX Insights to deliver information in real-time,” said Mike Downey, tech lead for Sports at Microsoft. “Alpine F1 Team’s use of Microsoft Azure is an example of enabling data driven decision making in a sport where every second matters.”

“We can easily scale up and down as required while adding new data streams with ease,” said Nathan Sykes, IT Business Systems and Data Science Director for the Alpine F1 Team.