Developing a long short-term memory-based model for forecasting the daily energy consumption of heating, ventilation, and air conditioning systems in buildings
Authors
Mendoza Pittí, Luis Agustín; Calderón Gómez, Huriviades; Gómez Pulido, José Manuel; Vargas Lombardo, Miguel; Castillo Sequera, José Luis; [et al.]Identifiers
Permanent link (URI): http://hdl.handle.net/10017/59997DOI: 10.3390/app11156722
ISSN: 2076-3417
Publisher
MDPI
Date
2021-07-15Bibliographic citation
Mendoza Pitti, L.A. [et al.], 2021, "Developing a long short-term memory-based model for forecasting the daily energy consumption of heating, ventilation, and air conditioning systems in buildings", Applied Sciences, vol. 11, no. 15, art. no. 6722, pp. 1-25.
Keywords
Daily energy consumption
Deep learning
Forecasting model
HVAC systems
Long short-term memory
Short-term forecast
Document type
info:eu-repo/semantics/article
Version
info:eu-repo/semantics/publishedVersion
Publisher's version
https://doi.org/10.3390/app11156722Rights
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
© 2021 The authors
Access rights
info:eu-repo/semantics/openAccess
Abstract
Forecasting the energy consumption of heating, ventilating, and air conditioning systems is important for the energy efficiency and sustainability of buildings. In fact, conventional models present limitations in these systems due to their complexity and unpredictability. To overcome this, the long short-term memory-based model is employed in this work. Our objective is to develop and evaluate a model to forecast the daily energy consumption of heating, ventilating, and air conditioning systems in buildings. For this purpose, we apply a comprehensive methodology that allows us to obtain a robust, generalizable, and reliable model by tuning different parameters. The results show that the proposed model achieves a significant improvement in the coefficient of variation of root mean square error of 9.5% compared to that proposed by international agencies. We conclude that these results provide an encouraging outlook for its implementation as an intelligent service for decision making, capable of overcoming the problems of other noise-sensitive models affected by data variations and disturbances without the need for expert knowledge in the domain. Se buscó pronosticar el consumo de energía de los sistemas de calefacción Heating, ventilating y aire acondicionado (HVAC) para la eficiencia energética de los edificios. En este estudio, se desarrolla un modelo de red neuronal artificial (RNA) recurrente del tipo Long short-term memory (LSTM) destinada a pronosticar el consumo de energía de un sistema HVAC en los edificios, en concreto una bomba de calor del Teatro Real de España. El trabajo comparó diferentes configuraciones del modelo con respecto a los datos reales proporcionados por el BMS del edificio y se identificó los hiperparámetros adecuados para el LSTM. El objetivo fue desarrollar y evaluar el modelo para pronosticar el consumo diario de energía de los sistemas HVAC, lográndose una predicción del uso de la energía según los criterios indicados por las directrices de American Society of Heating, Refrigerating and Air-Conditioning Engineers ASHRAE, The International Performance Measurement and Verification Protocol IPMVP y The Federal Energy Management Program organismos que validan un modelo HVAC. La contribución del solicitante se centró en el diseño del LSTM, y en la validación de las pruebas con los datos experimentales, así como en el análisis de los resultados obtenidos.
Files in this item
Files | Size | Format |
|
---|---|---|---|
Developing_Mendoza_Appl_Sci_20 ... | 550.8Kb |
|
Files | Size | Format |
|
---|---|---|---|
Developing_Mendoza_Appl_Sci_20 ... | 550.8Kb |
|
Collections
- CCOMPUT - Artículos [86]