As data is at the heart of the industry 4.0, 11 large international groups and the TAILOR network challenge european students from Oct 3 to Dec 3, with the Smarter Mobility Data Challenge for a Greener Future on Codalab. The challenge has been developped by INRIA scientists Marc Schoenaeur and Sebastien Treguer in collaboration with the industrial groups behind ManifesteIA.
About the challenge
The Smarter Mobility Data Challenge aims at testing statistical and machine learning forecasting models to forecast the states of a set of charging station in the paris area at different geographical resolution. It’s open for European students interested in data science and AI, and the prize is a mystery trip in Leonardo da Vinci’s footsteps. More information can be found on the Codalab platform.
Important dates and events
3-Oct-22 17:00:00 CET: Kick-off webinar
3-Oct-22 19:00:00 CET: Challenge opening
13-Oct-22 17:00:00 CET: Data Viz Presentation and Q&A
20-Oct-22 17:00:00 CET: Benchmark Presentation and Q&A
… TBD (HR sessions)
30-Nov-22 23:59:00 CET: Entering final phase of the challenge
3-Dec-22 17:00:00 CET: Challenge closing
Background
Transport represents almost a quarter of Europe greenhouse gas emissions. The development of electrical vehicles joinly with a low-carbon energy mix can help reducing these emissions and support the transportation sector in its low-carbon transition.
Electric mobility development entails new needs for energy providers and consumers. Businesses and researchers are proposing solutions including pricing strategies and smart charging. The goal of these solutions is to avoid dramatically shifting EV users’ behaviours and power plants production schedules. However, their implementation requires a precise understanding of charging behaviours. Thus, EV load models are necessary in order to better understand the impacts of EVs on the grid. With this information, the merit of EV charging strategies can be realistically assessed.
Forecasting occupation of a charging station can thus be a crucial need for utilities to optimize their production units in accordance with charging needs. On the user side, having information about when and where a charging station will be available is of course of interest.