LSTM recurrent neural network for energy demand forecasting

Abstract—Recurrent Neural Networks (RNN) of the Long Short Term Memory (LSTM) type provide high accuracy in predicting sequential models in various application domains. As in most process control problems, their dynamics include non manipulated variables that need to be predicted. This paper propose...

Descripción completa

Detalles Bibliográficos
Autores principales: Alarcón, Rodrigo Germán, Alarcón, Martín Alejandro, González, Alejandro H., Ferramosca, Antonio
Formato: Documento de conferencia publisherVersion
Lenguaje:Inglés
Inglés
Publicado: 2024
Materias:
Recurrent neural network, Long short term memory, Forecasting, Energy demand, Economic model predic tive control.
Acceso en línea:http://hdl.handle.net/20.500.12272/11218
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-11218
record_format dspace
spelling I68-R174-20.500.12272-112182024-08-01T22:51:52Z LSTM recurrent neural network for energy demand forecasting Alarcón, Rodrigo Germán Alarcón, Martín Alejandro González, Alejandro H. Ferramosca, Antonio Recurrent neural network, Long short term memory, Forecasting, Energy demand, Economic model predic tive control. Abstract—Recurrent Neural Networks (RNN) of the Long Short Term Memory (LSTM) type provide high accuracy in predicting sequential models in various application domains. As in most process control problems, their dynamics include non manipulated variables that need to be predicted. This paper proposes using an LSTM neural network for energy demand forecasting, which applies to an Economic Model Predictive Control (EMPC) as a forecasting tool. For the training, data are taken from a three-phase intelligent power quality analyser located at the National Technological University, Reconquista Regional Faculty (Santa Fe, Argentina). A recursive strategy is used to update the state of the neural network and forecast over different prediction horizons. The accuracy achieved in training the neural network is measured using the root mean square error (RMSE) metric. Experimental results show that the proposed LSTM neural network has excellent generalisation capability. Fil: Alarcón, Rodrigo G. Universidad Tecnológica Nacional. Facultad Regional Reconquista; Argentina. Fil: Alarcón, Martín A. Universidad Tecnológica Nacional. Facultad Regional Reconquista; Argentina. Fil: González, Alejandro H. Universidad Nacional del Litoral; Argentina. Fil: Ferramosca, Antonio. Università degli Studi di Bergamo; Italia. 2024-08-01T22:51:52Z 2024-08-01T22:51:52Z 2023-05-16 info:eu-repo/semantics/conferenceObject publisherVersion 28◦ Congreso Argentino de Control Automático AADECA’23 978-987-46859-4-0 http://hdl.handle.net/20.500.12272/11218 eng eng openAccess Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional Rodrigo G. Alarcón CC BY-NC (Autoría – No Comercial) pdf
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
Inglés
topic Recurrent neural network, Long short term memory, Forecasting, Energy demand, Economic model predic tive control.
spellingShingle Recurrent neural network, Long short term memory, Forecasting, Energy demand, Economic model predic tive control.
Alarcón, Rodrigo Germán
Alarcón, Martín Alejandro
González, Alejandro H.
Ferramosca, Antonio
LSTM recurrent neural network for energy demand forecasting
topic_facet Recurrent neural network, Long short term memory, Forecasting, Energy demand, Economic model predic tive control.
description Abstract—Recurrent Neural Networks (RNN) of the Long Short Term Memory (LSTM) type provide high accuracy in predicting sequential models in various application domains. As in most process control problems, their dynamics include non manipulated variables that need to be predicted. This paper proposes using an LSTM neural network for energy demand forecasting, which applies to an Economic Model Predictive Control (EMPC) as a forecasting tool. For the training, data are taken from a three-phase intelligent power quality analyser located at the National Technological University, Reconquista Regional Faculty (Santa Fe, Argentina). A recursive strategy is used to update the state of the neural network and forecast over different prediction horizons. The accuracy achieved in training the neural network is measured using the root mean square error (RMSE) metric. Experimental results show that the proposed LSTM neural network has excellent generalisation capability.
format Documento de conferencia
publisherVersion
author Alarcón, Rodrigo Germán
Alarcón, Martín Alejandro
González, Alejandro H.
Ferramosca, Antonio
author_facet Alarcón, Rodrigo Germán
Alarcón, Martín Alejandro
González, Alejandro H.
Ferramosca, Antonio
author_sort Alarcón, Rodrigo Germán
title LSTM recurrent neural network for energy demand forecasting
title_short LSTM recurrent neural network for energy demand forecasting
title_full LSTM recurrent neural network for energy demand forecasting
title_fullStr LSTM recurrent neural network for energy demand forecasting
title_full_unstemmed LSTM recurrent neural network for energy demand forecasting
title_sort lstm recurrent neural network for energy demand forecasting
publishDate 2024
url http://hdl.handle.net/20.500.12272/11218
work_keys_str_mv AT alarconrodrigogerman lstmrecurrentneuralnetworkforenergydemandforecasting
AT alarconmartinalejandro lstmrecurrentneuralnetworkforenergydemandforecasting
AT gonzalezalejandroh lstmrecurrentneuralnetworkforenergydemandforecasting
AT ferramoscaantonio lstmrecurrentneuralnetworkforenergydemandforecasting
_version_ 1809230382138130432

Ejemplares similares