Load Forecasting for Different Prediction Horizons using ANN and ARIMA models

Isabella Zuleta-Elles; Aiskel Bautista-Lopez; Milton J. Catano-Valderrama; Luis G. Marin; Guillermo Jimenez-Estevez; Patricio Mendoza-Araya

doi:10.1109/CHILECON54041.2021.9702913

Load Forecasting for Different Prediction Horizons using ANN and ARIMA models

Isabella Zuleta-Elles
, Aiskel Bautista-Lopez
, Milton J. Catano-Valderrama
, Luis G. Marin
, Guillermo Jimenez-Estevez
, Patricio Mendoza-Araya

Universidad de los Andes Colombia
Universidad de Chile

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

8 Citas (Scopus)

Resumen

Accurate forecasting of renewable energy resources and load has a crucial role in the overall operation efficiency and energy system integration of microgrids. In addition to this, in comparison with conventional power systems, the behaviour of microgrids loads presents higher frequency changes, which means greater volatility and higher uncertainty. In order to improve the robustness of microgrid energy management, and define through two different prediction techniques the best model for load forecasting, this paper provides a substantial review of theoretical Short Term forecasting methodologies, specifically Artificial Neural Network and ARIMA model, for microgrids loads. Using data from a real microgrid, the ANN model demonstrated a better performance than the ARIMA model in the forecasting results evaluated through specific metrics such as RMSE or MAE.

Idioma original	Inglés
Título de la publicación alojada	2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
Editorial	Institute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)	9781665408738
DOI	https://doi.org/10.1109/CHILECON54041.2021.9702913
Estado	Publicada - 2021
Publicado de forma externa	Sí
Evento	2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021 - Virtual, Online, Chile Duración: 06 dic 2021 → 09 dic 2021

Serie de la publicación

Nombre	2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021

Conferencia

Conferencia	2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
País/Territorio	Chile
Ciudad	Virtual, Online
Período	06/12/21 → 09/12/21

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

ODS 7: Energía asequible y no contaminante

Acceder al documento

10.1109/CHILECON54041.2021.9702913

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Zuleta-Elles, I., Bautista-Lopez, A., Catano-Valderrama, M. J., Marin, L. G., Jimenez-Estevez, G., & Mendoza-Araya, P. (2021). Load Forecasting for Different Prediction Horizons using ANN and ARIMA models. En 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021 (2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CHILECON54041.2021.9702913

Zuleta-Elles, Isabella ; Bautista-Lopez, Aiskel ; Catano-Valderrama, Milton J. et al. / Load Forecasting for Different Prediction Horizons using ANN and ARIMA models. 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021).

@inproceedings{76e2d21ca4424bb18476700924f8b98b,

title = "Load Forecasting for Different Prediction Horizons using ANN and ARIMA models",

abstract = "Accurate forecasting of renewable energy resources and load has a crucial role in the overall operation efficiency and energy system integration of microgrids. In addition to this, in comparison with conventional power systems, the behaviour of microgrids loads presents higher frequency changes, which means greater volatility and higher uncertainty. In order to improve the robustness of microgrid energy management, and define through two different prediction techniques the best model for load forecasting, this paper provides a substantial review of theoretical Short Term forecasting methodologies, specifically Artificial Neural Network and ARIMA model, for microgrids loads. Using data from a real microgrid, the ANN model demonstrated a better performance than the ARIMA model in the forecasting results evaluated through specific metrics such as RMSE or MAE.",

keywords = "ARIMA, Artificial Neural Networks, Energy Management System, Microgrids, Short Term Load Forecasting",

author = "Isabella Zuleta-Elles and Aiskel Bautista-Lopez and Catano-Valderrama, \{Milton J.\} and Marin, \{Luis G.\} and Guillermo Jimenez-Estevez and Patricio Mendoza-Araya",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021 ; Conference date: 06-12-2021 Through 09-12-2021",

year = "2021",

doi = "10.1109/CHILECON54041.2021.9702913",

language = "English",

series = "2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021",

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

booktitle = "2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021",

address = "United States",

}

Zuleta-Elles, I, Bautista-Lopez, A, Catano-Valderrama, MJ, Marin, LG, Jimenez-Estevez, G & Mendoza-Araya, P 2021, Load Forecasting for Different Prediction Horizons using ANN and ARIMA models. En 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021. 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021, Virtual, Online, Chile, 06/12/21. https://doi.org/10.1109/CHILECON54041.2021.9702913

Load Forecasting for Different Prediction Horizons using ANN and ARIMA models. / Zuleta-Elles, Isabella; Bautista-Lopez, Aiskel; Catano-Valderrama, Milton J. et al.
2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021).

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

TY - GEN

T1 - Load Forecasting for Different Prediction Horizons using ANN and ARIMA models

AU - Zuleta-Elles, Isabella

AU - Bautista-Lopez, Aiskel

AU - Catano-Valderrama, Milton J.

AU - Marin, Luis G.

AU - Jimenez-Estevez, Guillermo

AU - Mendoza-Araya, Patricio

PY - 2021

Y1 - 2021

N2 - Accurate forecasting of renewable energy resources and load has a crucial role in the overall operation efficiency and energy system integration of microgrids. In addition to this, in comparison with conventional power systems, the behaviour of microgrids loads presents higher frequency changes, which means greater volatility and higher uncertainty. In order to improve the robustness of microgrid energy management, and define through two different prediction techniques the best model for load forecasting, this paper provides a substantial review of theoretical Short Term forecasting methodologies, specifically Artificial Neural Network and ARIMA model, for microgrids loads. Using data from a real microgrid, the ANN model demonstrated a better performance than the ARIMA model in the forecasting results evaluated through specific metrics such as RMSE or MAE.

AB - Accurate forecasting of renewable energy resources and load has a crucial role in the overall operation efficiency and energy system integration of microgrids. In addition to this, in comparison with conventional power systems, the behaviour of microgrids loads presents higher frequency changes, which means greater volatility and higher uncertainty. In order to improve the robustness of microgrid energy management, and define through two different prediction techniques the best model for load forecasting, this paper provides a substantial review of theoretical Short Term forecasting methodologies, specifically Artificial Neural Network and ARIMA model, for microgrids loads. Using data from a real microgrid, the ANN model demonstrated a better performance than the ARIMA model in the forecasting results evaluated through specific metrics such as RMSE or MAE.

KW - ARIMA

KW - Artificial Neural Networks

KW - Energy Management System

KW - Microgrids

KW - Short Term Load Forecasting

UR - https://www.scopus.com/pages/publications/85126915107

U2 - 10.1109/CHILECON54041.2021.9702913

DO - 10.1109/CHILECON54041.2021.9702913

M3 - Conference contribution

AN - SCOPUS:85126915107

T3 - 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021

BT - 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021

Y2 - 6 December 2021 through 9 December 2021

ER -

Zuleta-Elles I, Bautista-Lopez A, Catano-Valderrama MJ, Marin LG, Jimenez-Estevez G, Mendoza-Araya P. Load Forecasting for Different Prediction Horizons using ANN and ARIMA models. En 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021). doi: 10.1109/CHILECON54041.2021.9702913

Load Forecasting for Different Prediction Horizons using ANN and ARIMA models

Resumen

Serie de la publicación

Conferencia

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto