Artificial intelligence for Smart Grids


The purpose of the "IA and Energy / Smartgrids" chair is to address the scientific challenges linked to the integration of renewable energies and new uses in energy systems using artificial intelligence techniques. This area is part of the 3D energy transition: Decarbonation, Decentralization and Digitization. In this context, some data are generated in large numbers by the various sensors disseminated in the electrical system or at the end users (Linky smart meter) while other data are largely missing. This later aspect complicates the complete observability of the electrical system that is necessary for a precise and efficient management and control especially as these systems concern critical infrastructures (vital systems). Traditional methods are limited and cannot handle the fast evolution of an evolving energy paradigm. Therefore, the contribution of artificial intelligence techniques to remove these obstacles is essential. However, the specificity is to couple data and physical models (hybrid models). Thus, the data gathered from these systems associated with Machine Learning processes should help improving various aspects of smartgrids including preventive maintenance models, real-time system diagnosis and control, from in an uncertain context, cyber security for SCADA / EMS/DMS systems, stability of microgrids with a high rate of renewable energy systems, optimization of field interventions for fault management in electrical networks, accurate forecasting models (production and consumption of energy with low grouping effect) or the distribution of intelligence in smart grids for dealing with new variable uses and energies. Furthermore, the decision-making process in an uncertain context requires support tools for the network operator. These tools often require the coupling of deep a,d reinforcement learning techniques. This also makes it possible to integrate the expertise of the grid operator into these decision models.


  • Aleksandr Petrusev presented his work MIAI days. He won the price of the best presentation of his session.
    • PhD thesis of Aleksandr Petrusev: “AI for managing Smartgrids” with ENEDIS
    • PhD thesis of Hassan Issa: “AI for microgrids with low inertia”
    • Post-Doc of Alyafi : “AI for short term consumption forecasting” with ENEDIS
    • Post-Doc of Sandra Castellanos-Paez: “Planning AI for smartgrids”
    • 3 Masters thesis
  • Upcoming projects :
    • Creation of an Energy Agora for the collection and use of energy data. Research Ingineer with IRT Nanoelec
    • PhD on AI for virtual power plants and price forecasting with Energy Pool
    • PhD on AI for Storage with ATOS World Grid



  • Aleksandr Petrusev, Rebecca Bauer, Remy Rigo-Mariani, Vincent Debusschere, Patrick Reignier et al. Comparing Time Series Classification And Forecasting To Automatically Detect Distributed Generation. IEEE PowerTech 2021, Jun 2021, Madrid, Spain.

  • A Distributed Model Predictive Control Framework for Grid-Friendly Distributed Energy Resources. Subramanian, L.; Debusschere, V.; Gooi, H. B. & Hadjsaid, N. IEEE Transactions on Sustainable Energy.

  • Lalitha Subramanian, Mamadou Goundiam, Vincent Debusschere, Hoay Gooi, Raphael Caire et al. Impact of the Interaction of Synchronous Machines and Virtual Inertia Provisions on the Small Signal Stability of Microgrids. CIRED 2021, Sep 2021, Online, France.

  • Audrey Moulichon, Mazen Alamir, Lauric Garbuio, Vincent Debusschere, Mustapha Rahmani et al. CIRED 2021 - 26th International Conference & Exhibition on Electricity Distribution, Sep 2021, Genève, Switzerland.

  • Coignard, J.; Janvier, M.; Debusschere, V.; Moreau, G.; Chollet, S. & Caire, R.Evaluating forecasting methods in the context of local energy communities. International Journal of Electrical Power & Energy Systems. Volume 131, October 2021, 106956.

  • Pas ds HAL_conference paper_ Subramanian, L.; Debusschere, V.; Gooi, H. B. & Hadjsaid, N. A Cooperative Rate-based Model Predictive Framework for Flexibility Management of DERs. IEEE Transactions on Energy Conversion _ August 2021IEEE Transactions on Energy Conversion PP(99):1-1.

  • Aleksandr Petrusev, Remy Rigo-Mariani, Vincent Debusschere, Patrick Reignier, Nouredine Hadjsaid. AUTOMATIC DETECTION OF DISTRIBUTED SOLAR GENERATION BASED ON EXOGENOUS INFORMATION. CIRED 2021, Sep 2021, Genève, Switzerland.

  • Z Fang, N Crimier, L Scanu, A Midelet, A Alyafi, B Delinchant.Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model. Energy and Buildings. Volume 245, 15 August 2021, 111053.

  • Moulichon, A.; Alamir, M.; Garbuio, L.; Debusschere, V.; Rahmani, M. A.; Boudinet, C.; Noris, W. & Hadjsaid, N., State observer to improve the VSG control stability, IEEE Annual Conference of the Industrial Electronics Society (IECON), 2020.

  • Moulichon, A.; Debusschere, V.; Garbuio, L.; Rahmani, M. A.; Alamir, M. & Hadjsaid, N., Standardization tests for the industrialization of grid-friendly Virtual Synchronous Generators, Bulletin of the Polish Academy of Sciences - Technical Sciences, 2020, 1-9.

  • Potel, B.; Cadoux, F.; Debusschere, V. & de Alvaro-Garcia, L., Impact of the periodicity of feeder re-allocation on the efficiency of under-frequency load shedding, IEEE PowerTech, 2019, 1-5.

  • Potel, B.; Debusschere, V.; Cadoux, F. & de Alvaro-Garcia, L., Scales and objectives for under-frequency load shedding. International Conference on Electricity Distribution, (CIRED), 2019, 1-5.

  • Zgolli, A., Collet, C., & Bobineau, C. (2019, June). DWS: a data placement approach for smart grid ecosystems. In Proceedings of the 23rd International Database Applications & Engineering Symposium (pp. 1-5).

  • Zgolli, A., Collet, C., & Bobineau, C. (2019, June). DWS: a data placement approach for smart grid ecosystems. In Proceedings of the 23rd International Database Applications & Engineering Symposium (pp. 1-5).

  • Hamdan, A., Cadoux, F., & Collet, C. (2019). Designing a Laboratory Setup to Experiment With Smart Metering for Smart Low Voltage Grid Applications, CIRED 2019.

  • Moulichon, A.; Garbuio, L.; Debusschere, V.; Rahmani, M. A. & Hadjsaid, N., A simplified synchronous machine model for virtual synchronous generator implementation, IEEE Power and Energy Society General Meeting, 2019, 1-5.

  • Potel, B.; Debusschere, V.; Cadoux, F. & Rudez, U. A real-time adjustment of conventional under-frequency load shedding thresholds, IEEE Transactions on Power Delivery, 2019, 34, 2272-2274.

  • Potel, B.; Cadoux, F.; de Alvaro-Garcia, L. & Debusschere, V., A Clustering-based Method for the Feeder Selection to Improve the Characteristics of Load Shedding, IET Smart Grid, 2019.

Published on  January 25, 2024
Updated on January 25, 2024