This has been one topic that I have been dying to write about and have finally gotten around to doing it. Analytics being as advanced as it is today, has touched upon almost every industry in more ways than one. For the love of the Michael Schumacher’s of the world, I chose to write on how advanced analytics has impacted the motorsports universe, Formula 1 in particular.
How often have we seen teams that were down in the dumps and roar back to life in the forthcoming seasons? Intense periods of testing during the off-season are not the only reason. The Red Bull racing F1 team was down in the dumps until 2009 and all of a sudden 4 straight constructor’s titles from 2010-2013. Bringing Sebastian Vettel on-board was a huge factor but the other factor was big data analytics.
To make my case, let me explain using the Mercedes-AMG Petronas team.
Lewis Hamilton sitting in his silver arrow has been unbeatable for the last 5 years. From 2014-till date, Mercedes have wreaked all kinds of havoc on the main stage. Constructor championships and driver championships have been won with ease. It was only in this season that Ferrari made significant improvements and mounted a massive challenge to the silver arrows of Mercedes.
The lead up to Race Day
Data analytics is a very critical factor when it comes to grand prix racing. A grand prix race is a 3 day weekend. On Friday, the car is set up with many sensors so that the team can monitor what is working and what is not. During qualifying on Saturday, only the most critical of sensors stay on and the rest are removed. On race day, the car setup must be identical to the car setup on Saturday.
Prepping for a race is a very painstakingly difficult process which needs to take into account the many variables like:
- The type of track and number of corners
- What was the car setup like last year and how did it perform?
- What down-force should you be gunning for?
- How quick should the transmission shifting be?
- Results of the wind tunnel tests
- How other teams are configuring their cars
Matt Harris who is the head of IT for the Mercedes-AMG Petronas team further attests to the fact that big data analytics plays a massive part in the team’s betterment. When there are many configurations while setting up the car, changing one will offset another and you obviously understand how the domino effect works. It is Harris’ job to determine which combination of configurations work best. There will be different settings, like one when fuel is low and the car needs to pit, one when tires are worn out, so on and so forth. Using data processing and analytics techniques to figure out which setting works best and what the contingency setting needs to be is an extremely difficult task. Harris says pre and post mortem of the event are the most key points in time for him and his team.
Visualizing the Win!
On the Friday of the grand prix, a silver arrow is loaded with close to 300 sensors which measure every tiny aspect of the car. These sensors measure things from transmission liquid temperature to car’s ride height. The sensors are removed from Saturday and Sunday cars to reduce weight.
Conditions from a 1000 times per second to 1 second intervals are sampled by these sensors. The Mercedes servers handle nearly 18000 channels of data. This amounts to about 500 GB of data per race and totals up to nearly 10 TB of data per season. Baseline data adds up to 30 TB as data from the previous year and the year before that is carried as well. To carry around this data securely, Mercedes stores it on solid-state PureStorage arrays.
The team employs 30 members to analyze the data on track and there are 30-200 pairs of eyes analyzing this data back at headquarters. Harris says that the amount of data generated is so much that the number of eyes to sift through this data is not enough.
To confirm race-day strategy, the team needs to weed out any abnormalities or problems if any. Mercedes uses TIBCO’s Spotfire visualization tool to analyze the race car. This further allows pre race configuration changes and strategy changes on race-day.
Harris states – “Having people look at all 500 GB of data is pointless. Just try to look at the anomalies and differences alone. Data Visualization enables us to make intelligent decisions quicker and faster. Sifting through tons of data to find out what may seems interesting is not required.”
The Analytical High Gear
Having the fastest car on track is how you win championships. To achieve this, transmission is extremely crucial. Whenever a driver shifts gears, a few 100 data points are received. Around 100 gear changes are made by a driver per lap and this easily translates into millions of data points per race.
Mercedes analyzes each gear shift across a variety of variables. A few of these are:
- Speed of the shift
- Speed of the engine
- Amount of wear on the clutch
- Oil temperature
This will give the team an idea of how much damage the transmission system is absorbing. If the damage is too much, the system will seize before the chequered flag.
If the driver ends the race with the transmission system in pristine condition, that is not a favourable outcome as well. Balancing the damage and performance is the end game and that is where analytics provides the solution to this tricky conundrum.
What is the conundrum you may ask! Should the gear change be smoother or quicker? Smoother means less wear and tear, but if it is smooth, it isn’t fast. Analytics allows the team to ensure fast gear changes with damage enough to last the race.
With a faster gear change 50 milliseconds per lap can be gained says Harris. 50 milliseconds in an F1 race is a lot. We have seen winners being decided with a difference of one thousandth of a second. Therefore, the tiny 50 millisecond advantage is a big advantage.
Making the Silver Arrow What It Is!
Along with Spotfire, various other data analysis tools and techniques are used by the Mercedes team. One of these is the Computational Fluid Dynamic (CFD) simulations which bring out the optimal balance between drag and downforce. Downforce is key to holding the center of gravity and keeping the cars glued to the track. However, this causes more drag and puts a limit on how quick the car can be on the straights.
In the latter stages of 2017, Harris’ team merged the capabilities of Stream base and Spotfire to achieve a closer to real time view. Working on more technological advancements like machine learning and deep learning frameworks, Harris says, his team and him have looked at a few of these frameworks and picking one seems to be a problem right now
Mercedes winning the Analytics game
At the beginning of the 2018 season the Mercedes-AMG Petronas Motorsport team struggled a bit and Hamilton didn’t win a race in the first few grand prix’s. We all saw how the season turned out with Mercedes taking home its 5th straight constructor’s championship. It seems like Harris made all the right calls even though they were a little slow out of the gates. The analytics team at Mercedes AMA Petronas is one of the best teams out there and the results are there for us to see.
All teams want to achieve faster straight line speed, holding corners at high speeds and the best aerodynamics. Mercedes seem to have cracked it and Ferrari have followed suit in 2018 by giving the silver arrow a run for its money. Redbull is never far behind. The 2019 season is going to be extremely interesting with the Redbull team shifting to Honda engines from the Renault engines.
Advanced analytics is the definitely the way for all teams to gain the competitive advantage that Mercedes has given the Silver Arrow.
Will it be the season of the prancing horse, the silver arrow or the bull? Whoever wields the analytics sword best, will be the last team standing!
Abhimanyu is a sportsman, an avid reader with a massive interest in sports. He is passionate about digital marketing and loves discussions about Big Data.