Reference : Deep Reinforcement Learning Solutions for Energy Microgrids Management
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/203831
Deep Reinforcement Learning Solutions for Energy Microgrids Management
English
François-Lavet, Vincent mailto [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore) >]
Taralla, David mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore) > >]
Ernst, Damien mailto [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Fonteneau, Raphaël mailto [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore) >]
Dec-2016
European Workshop on Reinforcement Learning (EWRL 2016)
Yes
International
European Workshop on Reinforcement Learning (EWRL 2016)
3-4 December 2016
[en] Reinforcement learning ; micro-grids
[en] This paper addresses the problem of efficiently operating the storage devices in an electricity microgrid featuring photovoltaic (PV) panels with both short- and long-term storage capacities. The problem of optimally activating the storage devices is formulated as a sequential decision making problem under uncertainty where, at every time-step, the uncertainty comes from the lack of knowledge about future electricity consumption and weather dependent PV production. This paper proposes to address this problem using deep reinforcement learning. To this purpose, a specific deep learning architecture has been designed in order to extract knowledge from past consumption and production time series as well as any available forecasts. The approach is empirically illustrated in the case of a residential customer located in Belgium.
CECi - Consortium des Équipements de Calcul Intensif
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/203831

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
EWRL_Francois-Lavet_et_al.pdfPublisher postprint656.19 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.