Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks

Alcántara Mata, Antonio; Galván, Inés M.; Aler, Ricardo

Publication:
Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks

dc.affiliation.dpto	UC3M. Departamento de Informática	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)	es
dc.contributor.author	Alcántara Mata, Antonio
dc.contributor.author	Galván, Inés M.
dc.contributor.author	Aler, Ricardo
dc.contributor.funder	Comunidad de Madrid	en
dc.contributor.funder	Universidad Carlos III de Madrid	en
dc.date.accessioned	2022-07-28T07:43:14Z
dc.date.available	2022-07-28T07:43:14Z
dc.date.issued	2022-09-01
dc.description.abstract	Deep neural networks (DNN) are becoming increasingly relevant for probabilistic forecasting because of their ability to estimate prediction intervals (PIs). Two different ways for estimating PIs with neural networks stand out: quantile estimation for posterior PI construction and direct PI estimation. The former first estimates quantiles, which are then used to construct PIs, while the latter directly obtains the lower and upper PI bounds by optimizing some loss functions, with the advantage that PI width is directly considered in the optimization process and thus may result in narrower intervals. In this work, two different DNN-based models are studied for direct PI estimation, and compared with DNN for quantile estimation in the context of solar and wind regional energy forecasting. The first approach is based on the recent quality-driven loss and is formulated to estimate multiple PIs with a single model. The second is a novel approach that employs hypernetworks (HN), where direct PI estimation is formulated as a multi-objective problem, returning a Pareto front of solutions that contains all possible coverage-width optimal trade-offs. This formulation allows HN to obtain optimal PIs for all possible coverages without increasing the number of network outputs or adjusting additional hyperparameters, as opposed to the first direct model. Results show that prediction intervals from direct estimation are narrower (up to 20%) than those of quantile estimation, for target coverages 70%–80% for all regions, and also 85%, 90%, and 95% depending on the region, while HN always achieves the required coverage for the higher target coverages.	en
dc.description.sponsorship	This publication is part of the I+D+i project PID2019-107455RBC22, funded by MCIN /AEI/10.13039/501100011033. This work was also supported by the Comunidad de Madrid Excellence Program. Funding for APC: Universidad Carlos III de Madrid (Read & Publish Agreement CRUE-CSIC 2022)	en
dc.identifier.bibliographicCitation	Alcántara, A., Galván, Inés M., Aler, R. (2022). Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks. Engineering Applications of Artificial Intelligence, 114, 105128.	en
dc.identifier.doi	https://doi.org/10.1016/j.engappai.2022.105128
dc.identifier.issn	0952-1976
dc.identifier.publicationtitle	ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE	en
dc.identifier.publicationvolume	114
dc.identifier.uri	https://hdl.handle.net/10016/35545
dc.identifier.uxxi	AR/0000030974
dc.language.iso	eng
dc.publisher	Elsevier
dc.relation.projectID	Gobierno de España. PID2019-107455RB-C22	es
dc.relation.projectID	AT-2022	es
dc.rights	© 2022 The Authors. Published by Elsevier Ltd.	en
dc.rights	Atribución-NoComercial-SinDerivadas 3.0 España
dc.rights.accessRights	open access	en
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.eciencia	Informática	es
dc.subject.other	direct prediction intervals estimation	en
dc.subject.other	quantile estimation	en
dc.subject.other	deep neural networks	en
dc.subject.other	hypernetworks	en
dc.subject.other	regional renewable energy forescasting	en
dc.subject.other	probabilistic forescasting	en
dc.title	Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks	en
dc.type	research article	*
dc.type.hasVersion	VoR	*
dspace.entity.type	Publication