Skip to Main content Skip to Navigation
Conference papers

Energy Management for Microgrids: a Reinforcement Learning Approach

Tanguy Levent 1 Philippe Preux 2 Erwan Le Pennec 3, 4 Jordi Badosa 5 Gonzague Henri 6 yvan Bonnassieux 1 
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
4 XPOP - Modélisation en pharmacologie de population
CMAP - Centre de Mathématiques Appliquées - Ecole Polytechnique, Inria Saclay - Ile de France
Abstract : This paper presents a framework based on reinforcement learning for energy management and economic dispatch of an islanded microgrid without any forecasting module. The architecture of the algorithm is divided in two parts: a learning phase trained by a reinforcement learning (RL) algorithm on a small dataset and the testing phase based on a decision tree induced from the trained RL. An advantage of this approach is to create an autonomous agent, able to react in real-time, considering only the past. This framework was tested on real data acquired at Ecole Polytechnique in France over a long period of time, with a large diversity in the type of days considered. It showed near optimal, efficient and stable results in each situation.
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02382232
Contributor : Tanguy Levent Connect in order to contact the contributor
Submitted on : Thursday, December 12, 2019 - 3:44:58 PM
Last modification on : Wednesday, March 23, 2022 - 3:51:20 PM
Long-term archiving on: : Friday, March 13, 2020 - 8:41:49 PM

File

Paper_Draft2.pdf
Files produced by the author(s)

Identifiers

Citation

Tanguy Levent, Philippe Preux, Erwan Le Pennec, Jordi Badosa, Gonzague Henri, et al.. Energy Management for Microgrids: a Reinforcement Learning Approach. ISGT-Europe 2019 - IEEE PES Innovative Smart Grid Technologies Europe, Sep 2019, Bucharest, France. pp.1-5, ⟨10.1109/ISGTEurope.2019.8905538⟩. ⟨hal-02382232⟩

Share

Metrics

Record views

373

Files downloads

1184