Last April 5 was the date chosen for the launch of the last awareness campaign of the IMPROVEMENT project. The awareness raising campaign counts on with almost 20 experts in advanced automatic control and artificial intelligence for energy management in buildings, mostly from France. A collaborative action was launched with the support of some of our main partners. Among them, the prestigious PROMES-CNRS laboratory from the University of Perpignan Via Domitia (UPVD), the National School of Mechanics and Aerotechnics (ENSMA) and the National Hydrogen Center (CNH2); the main beneficiary of the project and the Andalusian Energy Agency coordinator of communication.
The day began with a welcome to the participants in which each of the partners present intervened, to continue with a brief tour and summary of what IMPROVEMENT is, what its fundamental objectives are, what steps have been followed so far and what achievements and milestones have been met since the project was officially launched in January 2020.
During the day held online, the different partners of the project had the opportunity to present their vision of the current situation in terms of energy efficiency and sustainability in public buildings with critical loads, delve into their role as members of IMPROVEMENT and offer real data on the main results achieved and future developments.
The awareness campaign was a great success among the attendees, especially highlighting the presentations made by Romain Bourdais (IETR/CentraleSupelec), Stéphane Ploix (G-SCOP/Grenoble Institute of Technology), Jean-Paul Gaubert (LIAS-ENSIP/University of Poitiers) and Nilza Manjate (SRD, LabCom@LIENOR).
The act concluded with the celebration of a round table where the main conclusions of the day were presented and the bases of the next steps to be followed within the project were laid.
Finally, topics of broad interest to the participants and members of the organization were addressed, such as the development and in-situ implementation of smart solutions for energy management in buildings based on model-based predictive control and artificial intelligence techniques, such as machine or deep learning, and associated challenges.