A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series

e-Archivo Repository

Show simple item record

dc.contributor.author Alonso Fernández, Andrés Modesto
dc.contributor.author Nogales Martin, Fco. Javier
dc.contributor.author Ruiz Mora, Carlos
dc.date.accessioned 2021-07-28T08:46:19Z
dc.date.available 2021-07-28T08:46:19Z
dc.date.issued 2020-10-02
dc.identifier.bibliographicCitation Alonso, A. M., Nogales, F. J. & Ruiz, C. (2020). A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series. Energies, 13(20), 5328.
dc.identifier.issn 1996-1073
dc.identifier.uri http://hdl.handle.net/10016/33161
dc.description This article belongs to the Special Issue Forecasting in Electricity Markets with Big Data and Artificial Intelligence.
dc.description.abstract Most electricity systems worldwide are deploying advanced metering infrastructures to collect relevant operational data. In particular, smart meters allow tracking electricity load consumption at a very disaggregated level and at high frequency rates. This data opens the possibility of developing new forecasting models with a potential positive impact on electricity systems. We present a general methodology that can process and forecast many smart-meter time series. Instead of using traditional and univariate approaches, we develop a single but complex recurrent neural-network model with long short-term memory that can capture individual consumption patterns and consumptions from different households. The resulting model can accurately predict future loads (short-term) of individual consumers, even if these were not included in the original training set. This entails a great potential for large-scale applications as once the single network is trained, accurate individual forecast for new consumers can be obtained at almost no computational cost. The proposed model is tested under a large set of numerical experiments by using a real-world dataset with thousands of disaggregated electricity consumption time series. Furthermore, we explore how geo-demographic segmentation of consumers may impact the forecasting accuracy of the model.
dc.description.sponsorship The authors gratefully acknowledge the financial support from the Spanish government through projects MTM2017-88979-P and PID2019-108311GB-I00/AEI/10.13039/501100011033, and from Fundación Iberdrola through “Ayudas a la Investigación en Energía y Medio Ambiente 2018”.
dc.format.extent 19
dc.language.iso eng
dc.publisher MDPI
dc.rights © 2020 by the authors.
dc.rights Atribución 3.0 España
dc.rights.uri http://creativecommons.org/licenses/by/3.0/es/
dc.subject.other Disaggregated time series
dc.subject.other Load forecasting
dc.subject.other Neural networks
dc.subject.other Smart meters
dc.title A Single Scalable LSTM Model for Short-Term Forecasting of Massive Electricity Time Series
dc.type article
dc.subject.eciencia Estadística
dc.identifier.doi https://doi.org/10.3390/en13205328
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. MTM2017-88979-P
dc.relation.projectID Gobierno de España. PID2019-108311GB-I00
dc.type.version publishedVersion
dc.identifier.publicationfirstpage 5328
dc.identifier.publicationissue 20
dc.identifier.publicationtitle Energies
dc.identifier.publicationvolume 13
dc.identifier.uxxi AR/0000027560
dc.contributor.funder Ministerio de Ciencia e Innovación (España)
dc.affiliation.dpto UC3M. Departamento de Estadística
dc.affiliation.instituto UC3M. Instituto UC3M - Santander de Big Data
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record