As the second day of stage 6 of the Tour de France unfolds in the Pyrenees, showcasing the world’s toughest cyclists, it’s not just the thrilling images of their battles that are being broadcasted worldwide. Simultaneously, a vast amount of real-time data from various sensors is being transformed into valuable insights for organizers, competitors, and fans observing the challenging climbs of the tour.
For the past nine years, NTT Data and Dimension Data, in collaboration with Amaury Sport Organisation (ASO), the Tour de France organizers, have been responsible for constructing and managing advanced digital pathways for the race. This partnership utilizes cutting-edge technologies to create a digital twin of the race, employing edge computing and cloud technologies to establish the world’s largest “connected stadium.” These digital pathways integrate layers of real-time information, replicating the dynamic aspects of the event digitally.
The foundation of the data collection process lies in the installation of tiny trackers on each bicycle. These trackers constantly transmit data including latitude, longitude, and speed over radio networks to race motorcycles, which then relay the information to a plane. From there, a microwave signal carries the data to the end of the race, where a truck-based edge computing device runs a containerized version of the real-time analytics platform.
Upon arrival, the data is fed into algorithms that calculate a range of race insights, such as rider groupings, their locations along the route, and the distances between groups. The locally processed data is then sent to a custom application that provides ASO officials with a detailed, real-time view of the race, independent of mobile coverage or other data transmission modes. Microsoft Surface Pro X devices power this application, ensuring sufficient battery life to outlast a race stage.
In addition to the bicycle trackers, other trackers are deployed in the official race vehicles and Shimano neutral-service vehicles to provide accurate vehicle locations. These trackers are connected via Transatel Sims. Previously, officials had to rely on radio communications for updates, but with the introduction of this detailed data collection and analytics system, they now have access to real-time insights.
The extensive network of sensors, edge computing, cloud infrastructure, real-time analytics, and machine learning operates in the background to deliver statistics and insights to various stakeholders, including fans, broadcasters, support crews, race organizers, and the LeTourData team.
Interestingly, all of this technological innovation takes place in Johannesburg, South Africa, at Dimension Data’s Tour de France data hub. This central command center receives race data from sensors positioned along the race route and is manned by a combination of technical experts and cycling specialists. The hub serves as the global digital war room for NTT, offering a hybrid support operation with team members both locally and worldwide, including on-site in France.
While the data remains in the cloud, certain data management tasks are performed manually and then sent from the hub to the processing platform in the Microsoft Azure cloud. For instance, the system must be informed if a rider switches bikes, ensuring that the data doesn’t mistakenly show the rider heading in the wrong direction because the damaged bike is now in a support vehicle.
The raw data collected during the race is often challenging to work with due to signal limitations in remote, mountainous areas and tunnels along the 3,404-kilometer route. In these regions, signals from the bikes may be lost for minutes at a time or become duplicated and inaccurate in terms of speed and position due to GPS limitations.
To address these challenges, the real-time analytics platform has been developed from scratch over the past four years using open-source frameworks like Apache NiFi and Apache Beam, as well as tens of thousands of lines of Python code. This platform cleans, interpolates, and transforms the data into useful, human-readable fields, such as distance from the start, gap to the previous rider, current braking force, or relative wind speed and direction.
Knowing a cyclist’s position within the peloton is only part of the excitement; predicting stage and race winners, as well as comparing rider and team strengths and strategies, are also of great interest to fans. To cater to these needs, NTT Data combined mathematical modeling with sports science expertise to develop their prediction models. These models generate near real-time predictions using cloud-based virtual machines on Microsoft Azure. The processed data is then delivered to racing teams, organizers, and fans.
The power of data is also harnessed in the Tour de France Femmes avec Zwift, a women’s cycling race that has been integrated with this platform for its second year. By leveraging these technological advancements, the Tour de France and the women’s race are equipped with data-driven insights, enhancing the experience for participants and spectators alike.
Marianne has been trained on relevant race information and the addition of generative AI into the mix should mean more satisfactory answers to questions posed by cycling fans on the cycling grand tour’s official digital platforms.
The post THE SA TEAM RESPONSIBLE FOR TECH AT THE TOUR DE FRANCE appeared first on Entertainment SA - South African Entertainment News, Celebrity and Lifestyle Online Magazine & Entertainment.
Post a Comment