Estimación del consumo energético de una vivienda

This paper presents the results of the comparison between three different numeric regression techniques used to forecast typical home electric power consumption values. The data used was real life hourly consumption data gathered from homes in the “Cooservicios” community of the city of Tunja (Colom...

Full description

Autores:
Bautista López, Diego Andrés
Mantilla Arias, Maria Paula
Tipo de recurso:
Fecha de publicación:
2020
Institución:
Universidad Santo Tomás
Repositorio:
Universidad Santo Tomás
Idioma:
spa
OAI Identifier:
oai:repository.usta.edu.co:11634/32684
Acceso en línea:
http://revistas.ustatunja.edu.co/index.php/ingeniomagno/article/view/2051
http://hdl.handle.net/11634/32684
Palabra clave:
regression
sizing
energy
comparison
forecast
regresión
dimensionamiento
energía
comparación
pronóstico
regressão
dimensionamento
energia
comparação
previsão
Rights
License
Derechos de autor 2020 Ingenio Magno
Description
Summary:This paper presents the results of the comparison between three different numeric regression techniques used to forecast typical home electric power consumption values. The data used was real life hourly consumption data gathered from homes in the “Cooservicios” community of the city of Tunja (Colombia). The results of the study suggest that a regression technique based on the comparison between the average and daily values yields the lowest Mean Square Error (MSE). Once the MSE is deemed acceptable, it is possible to utilize the model to forecast power consumption with a relative degree of confidence. This comparison is made with the purpose of improving the dimensioning of renewable energy systems, based on the electricity consumption determined according to the predictions, achieving efficient systems that meet the needs of each one of the homes.