Project manager at the CMA

Prof. Gilles GUERASSIMOFF

https://cv.hal.science/gilles-guerassimoff

Project duration

4 years (2019-2023)

Research team involved at the CMA

Data and machine learning

Project type

ADEME – Programme d’Investissements d’Avenir

Partners

  • Idex
  • ARMINES
  • CEA Tech
  • Métropole Nice Côte d’Azur

Project description

Context:

The Nice Méridia eco-district aims to build 537,000 m² (housing, shops, university, crèche, services) by 2029. In this context, 3 objectives have been set by the local authority and the developer (EPA Plaine du Var):

  • Involving local residents and users in a local energy economy or dynamic;
  • Making the most of local energy sources: local renewable energy sources must account for more than 70% of the overall energy mix.
  • Developing an eco-system of innovative technological and economic solutions on an industrial scale

To achieve this, Nice Méridia has a number of assets and tools to implement: the construction of a geothermal heating and cooling network, the installation of PV systems in all buildings, and the possibility of thermal, refrigeration and electrical storage.

Objectives:

Designated by the Nice Côte d’Azur metropolitan authority as the local energy pilot for the eco-neighbourhood, in particular through the construction and operation of the future heating and cooling network, Idex and its partners plan to develop a portfolio of tools and services associated with the management of a multi-energy Smart Grid at the scale of the eco-neighbourhood. The innovations envisaged include

  • An innovative thermal storage solution using phase-change materials, in partnership with the CEA
  • Control of a multi-energy SmartGrid system using Hypervision and energy optimisation algorithms developed by Armines, to enable: management of self-consumption of photovoltaic energy, development of diffuse flexibilities, optimised control of electric vehicle recharging or public lighting, etc.

The aim of the proposed project is to demonstrate the technical and economic feasibility of such solutions in order to replicate and industrialise this range of services on other projects.

Publications and communications relating to the project

Dhekra Bousnina, Gilles Guerassimoff. OPTIMAL MULTI-ENERGY MANAGEMENT IN SMART ENERGY SYSTEMS: A DEEP REINFORCEMENT LEARNING APPROACH AND A CASE-STUDY ON A FRENCH ECO-DISTRICT. Smart Energy Systems, International Conference, Energy Cluster Denmark; AAlborg University Denmark, Sep 2023, Copenhaguen, Denmark. ⟨hal-04323498⟩

Dhekra Bousnina, Gilles Guerassimoff. Deep Reinforcement Learning for Optimal Energy Management of Multi-energy Smart Grids. Lecture Notes in Computer Science, 2022, pp.15 – 30. ⟨10.1007/978-3-030-95470-3_2⟩. ⟨hal-03587262⟩

Dhekra Bousnina, Gilles Guerassimoff. Multi-energy optimization in Smart Grids: a Deep Reinforcement Learning approach. SophI.A Summit, Nov 2020, Sophia-Antipolis, France. ⟨hal-03021016⟩

Dhekra Bousnina, Gilles Guerassimoff. Machine Learning methods to assist multi-energy systems optimization in a Smart Grid. SOPH.I.A Summit, Nov 2019, Sophia Antipolis, France. ⟨hal-02433485⟩