Unpublished conference/Abstract (Scientific congresses and symposiums)
Powertech 2021 presentation: Deep learning-based multi-output quantile forecasting of PV generation
Dumas, Jonathan
2021Powertech 2021
 

Files


Full Text
Powertech_87_DL.pdf
Author postprint (233.15 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Quantile forecasting; probabilistic PV forecasting; LSTM; encoder- decoder
Abstract :
[en] This paper develops probabilistic PV forecasters by taking advantage of recent breakthroughs in deep learning. It tailored forecasting tool, named encoder-decoder, is implemented to compute intraday multi-output PV quantiles forecasts to efficiently capture the time correlation. The models are trained using quantile regression, a non-parametric approach that assumes no prior knowledge of the probabilistic forecasting distribution. The case study is composed of PV production monitored on-site at the University of Liège (ULiège), Belgium. The weather forecasts from the regional climate model provided by the Laboratory of Climatology are used as inputs of the deep learning models. The forecast quality is quantitatively assessed by the continuous ranked probability and interval scores. The results indicate this architecture improves the forecast quality and is computationally efficient to be incorporated in an intraday decision-making tool for robust optimization.
Disciplines :
Energy
Computer science
Electrical & electronics engineering
Author, co-author :
Dumas, Jonathan  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart-Microgrids
Language :
English
Title :
Powertech 2021 presentation: Deep learning-based multi-output quantile forecasting of PV generation
Publication date :
June 2021
Event name :
Powertech 2021
Event organizer :
IEEE
Event date :
28/06/2021 - 02/07/2021
By request :
Yes
Audience :
International
References of the abstract :
paper in open-access: http://hdl.handle.net/2268/252357
Available on ORBi :
since 04 June 2021

Statistics


Number of views
82 (6 by ULiège)
Number of downloads
21 (3 by ULiège)

Bibliography


Similar publications



Contact ORBi