AWS has been working with Formula One (F1) since the middle of 2018. “We formed our collaboration strategically,” says AWS principal sports partnership manager, Neil Ralph. Data is collected during each race weekend, and is processed and analysed to provide insights for F1 fans to enable broadcasters to deliver new insights to the millions of people watching F1 around the world.
“We collect a huge amount of data. In fact, this generation of Formula One cars creates more than a million data points per second. The volume of data available from the sensors that are on board the car and from the trackside equipment that Formula One deploys at every race circuit provides huge opportunities for the teams themselves to leverage technology for the benefit of team performance and race strategy,” he says.
As an example, in 2020, commemorating the 70th anniversary of the sport, AWS machine learning services was used to ask that question of who is the fastest racing F1 driver of all time using all the historic data that Formula One holds. As Ralph points out, there are 70 years of results and information on all of the drivers that have ever competed in Formula One. But he adds: “The purest form of information is in qualifying, where cars have the least amount of fuel on board, the softest tyre compound and drivers are doing their level best to beat everyone in the field.”
But, more importantly, for Ralph, the most accurate test of a driver’s ability is whether he can beat his teammate in the next garage. “Using the teammate relationship we removed the effect of the car to achieve relative comparison across the entire field of drivers that have ever raced in Formula One.” While he admits the technical challenge of answering this question was both “a bit of fun, but also a great use of technology”, the analysis determined that Ayrton Senna is the fastest driver of all time.
“Formula one’s all about telling a story,” says Ryan Kirk, lead cloud architect at F1. “You’ve got the main race, but there’s also so many stories that happen in the background and a lot of that’s data-driven.” Kirk says the technology AWS provides has enabled F1 to provide real time insights using real time streaming of data coming from millions of data points per second. “We’re able to process that data in real time to provide behind the scenes insights that a viewer wouldn’t really see on a traditional broadcast.”
He says these insights tell these individual stories to provide the viewer with more information on what is really going on during an F1 race. “We transmit 500Tbytes of data from the track back to the UK per event.” A lot of that data goes into AWS and is processed.
For Kirk, every race is different. “In Formula One, new features are released at every race,” he says. These include extra functionality to expand fan user experience, such as using data insights to tell more stories and so create a richer viewer experience. Each race event is used to develop proof of concept functionality and prototyping. “We test them during an event to see what value they bring to the products that we’re trying to deliver,” Kirk adds.
