Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks

Xavier Serrano-Guerrero; Ricardo Prieto-Galarza; Esteban Huilcatanda; Juan Cabrera-Zeas; Guillermo Escriva-Escriva

doi:10.1109/ROPEC.2017.8261630

Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks

Xavier Serrano-Guerrero
, Ricardo Prieto-Galarza
, Esteban Huilcatanda
, Juan Cabrera-Zeas
, Guillermo Escriva-Escriva

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución de conferencia › revisión exhaustiva

7 Citas (Scopus)

Resumen

Forecasting of electricity demand is a fundamental requirement for the energy sector since from its results important decisions are taken. The areas involved are maintenance of electrical networks, demand growth, increased installed capacity, among others, whose lack of precision can take high economic costs. In this work, we propose a method based on backpropagation neural networks and election of key variables as inputs. The number of neurons in the hidden layer was optimized. To avoid the overtraining the best time range of data was defined. The results show that the method works particularly well for short-term forecasting (24 or 48 hours).

Idioma original	Inglés
Título de la publicación alojada	2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017
Editorial	Institute of Electrical and Electronics Engineers Inc.
Páginas	1-5
Número de páginas	5
ISBN (versión digital)	9781538608197
DOI	https://doi.org/10.1109/ROPEC.2017.8261630
Estado	Publicada - 16 ene. 2018
Evento	2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017 - Ixtapa, Guerrero, México Duración: 8 nov. 2017 → 10 nov. 2017

Serie de la publicación

Nombre	2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017
Volumen	2018-January

Conferencia

Conferencia	2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017
Título abreviado	ROPEC 2017
País/Territorio	México
Ciudad	Ixtapa, Guerrero
Período	8/11/17 → 10/11/17

Nota bibliográfica

Publisher Copyright:
© 2017 IEEE.

Areas de Conocimiento del CACES

317A Electricidad y energía

Acceder al documento

10.1109/ROPEC.2017.8261630

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Serrano-Guerrero, X., Prieto-Galarza, R., Huilcatanda, E., Cabrera-Zeas, J., & Escriva-Escriva, G. (2018). Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks. En 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017 (pp. 1-5). (2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROPEC.2017.8261630

Serrano-Guerrero, Xavier ; Prieto-Galarza, Ricardo ; Huilcatanda, Esteban et al. / Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks. 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-5 (2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017).

@inproceedings{ea92bd38b33644ea8fc2b8ae21d0a087,

title = "Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks",

abstract = "Forecasting of electricity demand is a fundamental requirement for the energy sector since from its results important decisions are taken. The areas involved are maintenance of electrical networks, demand growth, increased installed capacity, among others, whose lack of precision can take high economic costs. In this work, we propose a method based on backpropagation neural networks and election of key variables as inputs. The number of neurons in the hidden layer was optimized. To avoid the overtraining the best time range of data was defined. The results show that the method works particularly well for short-term forecasting (24 or 48 hours).",

keywords = "artificial neural networks, electricity demand, forecasting, prediction",

author = "Xavier Serrano-Guerrero and Ricardo Prieto-Galarza and Esteban Huilcatanda and Juan Cabrera-Zeas and Guillermo Escriva-Escriva",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017 ; Conference date: 08-11-2017 Through 10-11-2017",

year = "2018",

month = jan,

day = "16",

doi = "10.1109/ROPEC.2017.8261630",

language = "English",

series = "2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--5",

booktitle = "2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017",

address = "United States",

}

Serrano-Guerrero, X, Prieto-Galarza, R, Huilcatanda, E, Cabrera-Zeas, J & Escriva-Escriva, G 2018, Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks. En 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017. 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017, Ixtapa, Guerrero, México, 8/11/17. https://doi.org/10.1109/ROPEC.2017.8261630

Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks. / Serrano-Guerrero, Xavier; Prieto-Galarza, Ricardo; Huilcatanda, Esteban et al.
2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-5 (2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017; Vol. 2018-January).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución de conferencia › revisión exhaustiva

TY - GEN

T1 - Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks

AU - Serrano-Guerrero, Xavier

AU - Prieto-Galarza, Ricardo

AU - Huilcatanda, Esteban

AU - Cabrera-Zeas, Juan

AU - Escriva-Escriva, Guillermo

PY - 2018/1/16

Y1 - 2018/1/16

N2 - Forecasting of electricity demand is a fundamental requirement for the energy sector since from its results important decisions are taken. The areas involved are maintenance of electrical networks, demand growth, increased installed capacity, among others, whose lack of precision can take high economic costs. In this work, we propose a method based on backpropagation neural networks and election of key variables as inputs. The number of neurons in the hidden layer was optimized. To avoid the overtraining the best time range of data was defined. The results show that the method works particularly well for short-term forecasting (24 or 48 hours).

AB - Forecasting of electricity demand is a fundamental requirement for the energy sector since from its results important decisions are taken. The areas involved are maintenance of electrical networks, demand growth, increased installed capacity, among others, whose lack of precision can take high economic costs. In this work, we propose a method based on backpropagation neural networks and election of key variables as inputs. The number of neurons in the hidden layer was optimized. To avoid the overtraining the best time range of data was defined. The results show that the method works particularly well for short-term forecasting (24 or 48 hours).

KW - artificial neural networks

KW - electricity demand

KW - forecasting

KW - prediction

UR - https://www.scopus.com/pages/publications/85046271698

U2 - 10.1109/ROPEC.2017.8261630

DO - 10.1109/ROPEC.2017.8261630

M3 - Conference contribution

AN - SCOPUS:85046271698

T3 - 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017

SP - 1

EP - 5

BT - 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017

Y2 - 8 November 2017 through 10 November 2017

ER -

Serrano-Guerrero X, Prieto-Galarza R, Huilcatanda E, Cabrera-Zeas J, Escriva-Escriva G. Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks. En 2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-5. (2017 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2017). doi: 10.1109/ROPEC.2017.8261630

Election of variables and short-term forecasting of electricity demand based on backpropagation artificial neural networks

Resumen

Serie de la publicación

Conferencia

Nota bibliográfica

Areas de Conocimiento del CACES

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto