A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models

Juan José Sáenz-Peñafiel; Jorge E. Luzuriaga; Lenin Guillermo Lemus-Zuñiga; Vanessa Solis-Cabrera

doi:10.1007/978-3-030-59194-6_36

A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models

Juan José Sáenz-Peñafiel
, Jorge E. Luzuriaga
, Lenin Guillermo Lemus-Zuñiga
, Vanessa Solis-Cabrera

Vicerrectorado de Investigación e Innovación

Polytechnic University of Valencia
Universidad de Cuenca

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Energy consumption and demand are two widely used terms necessary to understand the functioning of the different mechanisms used in electrical energy transactions. In this article, the design and construction of a comprehensive solution to forecast future trends in electricity transactions using the historical data and two auto-regressive models were considered. Simple linear regression and a complete model such as ARIMA. We compared these models to find which one best suits the type of data considering their strengths and weaknesses for this specific case. Finally, to complete the comprehensive solution, the results are presented to the final user. This solution is mainly aimed at professionals who carry out activities related to contracting and managing electricity supply in public institutions. This solution pretends to collaborate to reduce energy demand and therefore, consumption.

Original language	English
Title of host publication	Systems and Information Sciences - Proceedings of ICCIS 2020
Editors	Miguel Botto-Tobar, Willian Zamora, Johnny Larrea Plúa, José Bazurto Roldan, Alex Santamaría Philco
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	443-454
Number of pages	12
ISBN (Print)	9783030591939
DOIs	https://doi.org/10.1007/978-3-030-59194-6_36
State	Published - 2021
Event	1st International Conference on Systems and Information Sciences, ICCIS 2020 - Manta, Ecuador Duration: 27 Jul 2020 → 29 Jul 2020

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1273 AISC
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	1st International Conference on Systems and Information Sciences, ICCIS 2020
Country/Territory	Ecuador
City	Manta
Period	27/07/20 → 29/07/20

Keywords

ARIMA
Auto-regressive models
Data capture
Energy
Energy demand
Prediction

Access to Document

10.1007/978-3-030-59194-6_36

Cite this

Sáenz-Peñafiel, J. J., Luzuriaga, J. E., Lemus-Zuñiga, L. G., & Solis-Cabrera, V. (2021). A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models. In M. Botto-Tobar, W. Zamora, J. Larrea Plúa, J. Bazurto Roldan, & A. Santamaría Philco (Eds.), Systems and Information Sciences - Proceedings of ICCIS 2020 (pp. 443-454). (Advances in Intelligent Systems and Computing; Vol. 1273 AISC). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-59194-6_36

Sáenz-Peñafiel, Juan José ; Luzuriaga, Jorge E. ; Lemus-Zuñiga, Lenin Guillermo et al. / A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models. Systems and Information Sciences - Proceedings of ICCIS 2020. editor / Miguel Botto-Tobar ; Willian Zamora ; Johnny Larrea Plúa ; José Bazurto Roldan ; Alex Santamaría Philco. Springer Science and Business Media Deutschland GmbH, 2021. pp. 443-454 (Advances in Intelligent Systems and Computing).

@inproceedings{0cdc157555c245cebc63640ab3d4de28,

title = "A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models",

abstract = "Energy consumption and demand are two widely used terms necessary to understand the functioning of the different mechanisms used in electrical energy transactions. In this article, the design and construction of a comprehensive solution to forecast future trends in electricity transactions using the historical data and two auto-regressive models were considered. Simple linear regression and a complete model such as ARIMA. We compared these models to find which one best suits the type of data considering their strengths and weaknesses for this specific case. Finally, to complete the comprehensive solution, the results are presented to the final user. This solution is mainly aimed at professionals who carry out activities related to contracting and managing electricity supply in public institutions. This solution pretends to collaborate to reduce energy demand and therefore, consumption.",

keywords = "ARIMA, Auto-regressive models, Data capture, Energy, Energy demand, Prediction",

author = "S{\'a}enz-Pe{\~n}afiel, \{Juan Jos{\'e}\} and Luzuriaga, \{Jorge E.\} and Lemus-Zu{\~n}iga, \{Lenin Guillermo\} and Vanessa Solis-Cabrera",

note = "Publisher Copyright: {\textcopyright} 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.; 1st International Conference on Systems and Information Sciences, ICCIS 2020 ; Conference date: 27-07-2020 Through 29-07-2020",

year = "2021",

doi = "10.1007/978-3-030-59194-6\_36",

language = "Ingl{\'e}s",

isbn = "9783030591939",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "443--454",

editor = "Miguel Botto-Tobar and Willian Zamora and \{Larrea Pl{\'u}a\}, Johnny and \{Bazurto Roldan\}, Jos{\'e} and \{Santamar{\'i}a Philco\}, Alex",

booktitle = "Systems and Information Sciences - Proceedings of ICCIS 2020",

}

Sáenz-Peñafiel, JJ, Luzuriaga, JE, Lemus-Zuñiga, LG & Solis-Cabrera, V 2021, A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models. in M Botto-Tobar, W Zamora, J Larrea Plúa, J Bazurto Roldan & A Santamaría Philco (eds), Systems and Information Sciences - Proceedings of ICCIS 2020. Advances in Intelligent Systems and Computing, vol. 1273 AISC, Springer Science and Business Media Deutschland GmbH, pp. 443-454, 1st International Conference on Systems and Information Sciences, ICCIS 2020, Manta, Ecuador, 27/07/20. https://doi.org/10.1007/978-3-030-59194-6_36

A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models. / Sáenz-Peñafiel, Juan José; Luzuriaga, Jorge E.; Lemus-Zuñiga, Lenin Guillermo et al.
Systems and Information Sciences - Proceedings of ICCIS 2020. ed. / Miguel Botto-Tobar; Willian Zamora; Johnny Larrea Plúa; José Bazurto Roldan; Alex Santamaría Philco. Springer Science and Business Media Deutschland GmbH, 2021. p. 443-454 (Advances in Intelligent Systems and Computing; Vol. 1273 AISC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models

AU - Sáenz-Peñafiel, Juan José

AU - Luzuriaga, Jorge E.

AU - Lemus-Zuñiga, Lenin Guillermo

AU - Solis-Cabrera, Vanessa

PY - 2021

Y1 - 2021

N2 - Energy consumption and demand are two widely used terms necessary to understand the functioning of the different mechanisms used in electrical energy transactions. In this article, the design and construction of a comprehensive solution to forecast future trends in electricity transactions using the historical data and two auto-regressive models were considered. Simple linear regression and a complete model such as ARIMA. We compared these models to find which one best suits the type of data considering their strengths and weaknesses for this specific case. Finally, to complete the comprehensive solution, the results are presented to the final user. This solution is mainly aimed at professionals who carry out activities related to contracting and managing electricity supply in public institutions. This solution pretends to collaborate to reduce energy demand and therefore, consumption.

AB - Energy consumption and demand are two widely used terms necessary to understand the functioning of the different mechanisms used in electrical energy transactions. In this article, the design and construction of a comprehensive solution to forecast future trends in electricity transactions using the historical data and two auto-regressive models were considered. Simple linear regression and a complete model such as ARIMA. We compared these models to find which one best suits the type of data considering their strengths and weaknesses for this specific case. Finally, to complete the comprehensive solution, the results are presented to the final user. This solution is mainly aimed at professionals who carry out activities related to contracting and managing electricity supply in public institutions. This solution pretends to collaborate to reduce energy demand and therefore, consumption.

KW - ARIMA

KW - Auto-regressive models

KW - Data capture

KW - Energy

KW - Energy demand

KW - Prediction

UR - https://www.scopus.com/pages/publications/85094118561

U2 - 10.1007/978-3-030-59194-6_36

DO - 10.1007/978-3-030-59194-6_36

M3 - Contribución a la conferencia

AN - SCOPUS:85094118561

SN - 9783030591939

T3 - Advances in Intelligent Systems and Computing

SP - 443

EP - 454

BT - Systems and Information Sciences - Proceedings of ICCIS 2020

A2 - Botto-Tobar, Miguel

A2 - Zamora, Willian

A2 - Larrea Plúa, Johnny

A2 - Bazurto Roldan, José

A2 - Santamaría Philco, Alex

PB - Springer Science and Business Media Deutschland GmbH

T2 - 1st International Conference on Systems and Information Sciences, ICCIS 2020

Y2 - 27 July 2020 through 29 July 2020

ER -

Sáenz-Peñafiel JJ, Luzuriaga JE, Lemus-Zuñiga LG, Solis-Cabrera V. A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models. In Botto-Tobar M, Zamora W, Larrea Plúa J, Bazurto Roldan J, Santamaría Philco A, editors, Systems and Information Sciences - Proceedings of ICCIS 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 443-454. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-59194-6_36

A Comprehensive Solution for Electrical Energy Demand Prediction Based on Auto-Regressive Models

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this