Image: ASO/Tour de France

while we look cyclists battling through the second day in the Pyrenees on stage 6 of the annual Tour de France, a 144km course from Tarbes to Cauterets-Cambasque, it’s not just footage of the world’s toughest cyclists in action that’s broadcast all over the world.

At the same time, real-time data streams from countless sensors are becoming useful information for organizers, competitors and fans watching some of the classic climbs on the course. For many years, crowds jockeyed for space along the 3,000+ km route to catch a glimpse of the peloton speeding by. Those spectators on the road had no way of monitoring the progress of individual riders or of predicting who might win the yellow jersey, and had to rely on radio and television broadcasts for race updates.

But in the age of connectivity and the Internet of Things, the world’s best cyclists race along a variety of advanced digital paths that are closely monitored by officials in real time. In association with the Amaury Sport Organization (ASO), the organizers of the Tour de France, NTT Data and Dimension Data are responsible for building and managing those routes for the ninth year. “The race is like a giant playground, or an incubator, for how to use technology,” Dimension Data’s vice president of applications and cloud, Lauren Wortmann, said in an interview with TechCentral on Thursday.

“We used cloud and edge computing technologies to create the world’s largest ‘connected stadium’ by creating a career digital twinthat combines layers of information in real time to digitally replicate all aspects of this highly dynamic event,” she said.

Data-driven insights and AI predictions on the “LeTourData” channels on Twitter, Instagram and TV keep fans informed about both races (the Tour de France and the women’s race, Tour de France Femmes avec Zwift ) and help ASO operations teams communicate and plan more efficiently.

At the center of the data collection are small trackers fitted to each bike. They transmit a constant stream of latitude, longitude and speed data via radio networks to racing motorcycles, which then transmit the information to an aircraft. From there, a microwave signal carries the data to the end of the race, where a truck edge computing The device runs a containerized version of the real-time analytics platform.


As the data arrives, it is fed into algorithms that calculate a variety of information about the race, such as groups of riders, their location along the route, and the distance between groups.

The locally processed data is then sent to a custom app that gives ASO officials a detailed, real-time view of what’s happening on the ground, without having to rely on cellular coverage or other modes of transmission. data.. The app runs on Microsoft Surface Pro X devices, which have enough battery life to last more than one race stage.

Other trackers on official racing vehicles are connected via Transatel Sims to provide precise vehicle locations. They have also been fitted to Shimano’s neutral service vehicles, which provide mechanical help to riders isolated from their team cars.

Until about two years ago, officials had to rely on radio communications to keep up to date, but now they have this level of detail on demand. It’s a great example of how IoT devices and cutting-edge computing have brought a new level of insight and efficiency to the Tour de France, with most of the technological innovation coming from the South Africans.

While the eyes of the world are on the runners, a complex and interconnected system of sensors, networks, edge computing, cloud, real-time analytics and machine learning is operating in the background to provide statistics and information to fans, broadcasters, support teams, the race organizers and the LeTourData equipment.


And it’s all happening on the other side of the world, in Johannesburg, at the Dimension Data Tour de France. data center. This is the central command center that receives the race data from the sensors at the race, and is staffed by a mix of technical specialists and riders.

“Dimension Data South Africa acts as the global digital war room for NTT, offering a hybrid support operation with team members around the world and on the ground in France. In 2022, we move to a hybrid model with a core support team based on the Bryanston campus. We also have team members in the ‘tech truck’ located at the end of each stage of the race, ensuring that any issues that require a hands-on approach are addressed on the ground in France,” said Wortmann.

While the data remains in the cloud, some of the data management is done manually and sent from the hub to the Microsoft Azure cloud processing platform. For example, the processing system should indicate that if a cyclist has switched bikes, perhaps after a crash, the data does not suddenly show the cyclist accelerating in the wrong direction because the damaged bike is now in a support vehicle.

The raw data is “messy” because there are many remote mountainous areas and tunnels along the 3,404km Tour de France route where bike signals are completely missing, sometimes by minutes. These signals may also be duplicated or inaccurate in terms of speed and position due to GPS limitations.

The real-time analytics platform has been built from the ground up by the team over the past four years, using open source frameworks including Apache NiFi, Apache Beam, and tens of thousands of lines of Python code. Cleans, interpolates, and transforms the data into useful, human-readable data fields, such as “distance from start”; “gap with previous cyclist”; “current braking force” or “relative wind speed and direction”.

Knowing where a rider is in the peloton at any given time is only half the fun – predicting stage and race winners is also top of mind for fans, as well as comparing rider and team strengths and strategies. So NTT Data combined mathematical modeling with the insights of a sports scientist to develop its own prediction models, generated in near real time using cloud-based virtual machines on Microsoft Azure. The processed data is then delivered to the racing teams, organizers and fans.

1688648072 600 The SA team behind the technology in the Tour de | perutren
Image: ASO/Tour de France

This platform also powers the Tour de France Femmes avec Zwift, now in its second year, bringing the power of data to the top of women’s cycling racing as well. The 2022 event saw the inaugural women’s race at La Super Planche des Belles Filles.

And this year, a virtual human commentator has been introduced: NTT has integrated ChatGPT generative AI into Marianne, its digital assistant, building on its existing machine learning, speech recognition, natural language processing and conversational AI capabilities. She is named after Marianne Martin, the first American woman to win a Tour de France.

Marianne received training on relevant information from the race and the addition of generative AI to the mix should mean more satisfying answers to questions posed by cycling fans on the official digital platforms of the great cycling tour. – © 2023 Central Media News

Get TechCentral’s daily newsletter