
The «PEPER» project
This is the question asked by Florence Ossart, Hossam Afifi and Jordi Badosa, whose « PEPER » project was selected by the DATAIA Institute as part of its 2018 call for « research » projects.
The world of electrical energy is facing significant structural changes: electricity use is constantly increasing, and climate challenges require an increase in the share of renewable energies in production (solar and wind).
Florence Ossart, professor at Laboratoire de Génie Electrique de Paris (CNRS, CentraleSupélec, Université Paris-Sud, Sorbonne Université), Hossam Afifi, professor at Télécom SudParis and Jordi Badosa, project manager at the École polytechnique within the Laboratoire de Météorologie Dynamique (CNRS, École polytechnique, ENS Paris-Saclay, Sorbonne Université) have decided to unite their disciplines (energy, telecom and weather) in order to introduce information systems into the electrical networks to communicate these two worlds between them. The DATAIA Institute offers them a workspace to make this project a reality.
« Prosumption »: adapting consumer behaviour to the resource available at the time it is available
The PEPER project will study 3 concepts that will need to be developed in order to create a balanced system for the efficient management of renewable energies: production, consumption and storage.
A first objective is to predict the production of electricity from renewable sources based on weather forecasts, which give, for example, the rate of sunshine, temperature, wind, etc., and to evaluate the quality of these forecasts.
Then, we have to study the behaviour of users to be able to predict their consumption: "Using data from mobile phones, for example, we will study human presence in a given place to predict their behaviour and energy consumption," Florence explains.
Finally, the difference between production and consumption must be compensated in real time by means of appropriate storage facilities on the one hand, but also by adapting consumption to production where possible. This is called "prosumption".
Production, consumption and storage form a network
"There is a lot of data," says Jordi, "from different sources (weather, consumption, mobility, production...) with different temporal and spatial resolutions. The idea is to understand how we can combine them to know the state of an electricity grid at a given time and make decisions on the collaborative management of this energy. »
The objective of the PEPER project is to collect data on the different actors of this network, and to use learning and Deep Reinforcement Learning techniques to develop algorithms for predicting the production and consumption of each actor, and then for cooperation between them.
"For this project, we have data from buildings on our campuses. The Paris-Saclay Urban Community will also provide us with a building to be wired to study the different consumptions. The objective is to create an algorithm that will use the collected data to better manage energy savings without compromising user comfort" says Hossam.
A collaborative project born in 2017
"We've been meeting for a year and trying to set up a project," says Jordi. We realized that, on the Saclay plateau, several laboratories of different disciplines deal with the subject of renewable energies, the notions of microgrids (self-production and energy consumption)... etc. We felt it necessary to approach them in an interdisciplinary manner."
Inspired by collaborations such as Allistene (1) or Ancre (2), the PEPER project will give concrete expression to this desire to bring together disciplines around the theme of energy.