Thèse soutenue

Modélisation et optimisation de micro réseaux sous incertitude avec une approche orientée agent

FR  |  
EN
Auteur / Autrice : Elizaveta Kusnetsova
Direction : Enrico Zio
Type : Thèse de doctorat
Discipline(s) : Eco-innovation
Date : Soutenance en 2014
Etablissement(s) : Versailles-St Quentin en Yvelines

Mots clés

FR

Mots clés contrôlés

Résumé

FR  |  
EN

This thesis concerns the energy management of electricity microgrids. The scientific contribution follows two directions: (i) modelling individual intelligence in energy management under uncertainty and (ii) microgrid energy management integrating diverse actors with conflicting objectives. Agent-Based Modelling (ABM) is used to describe the dynamics of microgrid actors operating under limited access to information, and operational and environmental uncertainties. The approaches considered to model individual intelligence in this thesis, Reinforcement Learning and Robust Optimization, provide each agent with the capability of making decision, adapting to the stochastic environment and interacting with other agents. The modelling frameworks developed have been tested on urban microgrids integrating different energy consumers, sources of renewable energy and storage facilities, for optimal energy management in terms of reliability and economic indicators under operational and environmental uncertainty, and components failures.