Publicado

2017-01-01

Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques

Palabras clave:

Predictive models, Load Forecasting, Gaussian Mixture Model, Mixture of models (en)

Descargas

Autores/as

  • Andrés Fernando Arciniegas Mejía Universidad de Nariño
  • David Esteban Imbajoa Universidad de Nariño
  • Javier Revelo Fuelagán Universidad de Nariño

The estimation of energy demand is not always straightforward or reliable, as one or several classes may fail in the prediction. In this study, a novel methodology of load forecasting is proposed. Three different configurations of weak Artificial Neural Networks perform a supervised classification of energy consumption data, each one providing an output vector of unreliable predicted data. Under the clustering method k-means, multiple patterns are identified, and then processed by the Gaussian Mixture Model in order to provide higher relevance to the more accurate predicted samples of data. The accuracy of the prediction is evaluated with the several error rate measurements. Finally, a mixture of the generated forecasts by the methods is performed, showing a lower error rate compared to the inputs predictions, therefore, a more reliable forecast.

Cómo citar

APA

Arciniegas Mejía, A. F., Imbajoa, D. E. y Revelo Fuelagán, J. (2017). Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques. Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL, 9. https://revistas.unal.edu.co/index.php/SICEL/article/view/64241

ACM

[1]
Arciniegas Mejía, A.F., Imbajoa, D.E. y Revelo Fuelagán, J. 2017. Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques. Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL. 9, (ene. 2017).

ACS

(1)
Arciniegas Mejía, A. F.; Imbajoa, D. E.; Revelo Fuelagán, J. Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques. SICEL 2017, 9.

ABNT

ARCINIEGAS MEJÍA, A. F.; IMBAJOA, D. E.; REVELO FUELAGÁN, J. Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques. Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL, [S. l.], v. 9, 2017. Disponível em: https://revistas.unal.edu.co/index.php/SICEL/article/view/64241. Acesso em: 10 feb. 2025.

Chicago

Arciniegas Mejía, Andrés Fernando, David Esteban Imbajoa, y Javier Revelo Fuelagán. 2017. «Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques». Simposio Internacional Sobre La Calidad De La Energía Eléctrica - SICEL 9 (enero). https://revistas.unal.edu.co/index.php/SICEL/article/view/64241.

Harvard

Arciniegas Mejía, A. F., Imbajoa, D. E. y Revelo Fuelagán, J. (2017) «Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques», Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL, 9. Disponible en: https://revistas.unal.edu.co/index.php/SICEL/article/view/64241 (Accedido: 10 febrero 2025).

IEEE

[1]
A. F. Arciniegas Mejía, D. E. Imbajoa, y J. Revelo Fuelagán, «Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques», SICEL, vol. 9, ene. 2017.

MLA

Arciniegas Mejía, A. F., D. E. Imbajoa, y J. Revelo Fuelagán. «Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques». Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL, vol. 9, enero de 2017, https://revistas.unal.edu.co/index.php/SICEL/article/view/64241.

Turabian

Arciniegas Mejía, Andrés Fernando, David Esteban Imbajoa, y Javier Revelo Fuelagán. «Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques». Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL 9 (enero 1, 2017). Accedido febrero 10, 2025. https://revistas.unal.edu.co/index.php/SICEL/article/view/64241.

Vancouver

1.
Arciniegas Mejía AF, Imbajoa DE, Revelo Fuelagán J. Forecasting of Energy Consumption Based on Gaussian Mixture Model and Classification Techniques. SICEL [Internet]. 1 de enero de 2017 [citado 10 de febrero de 2025];9. Disponible en: https://revistas.unal.edu.co/index.php/SICEL/article/view/64241

Descargar cita

Visitas a la página del resumen del artículo

220

Descargas

Los datos de descargas todavía no están disponibles.