TY - JOUR
T1 - Analysis of the Integration of Drift Detection Methods in Learning Algorithms for Electrical Consumption Forecasting in Smart Buildings
AU - Mariano-Hernández, Deyslen
AU - Hernández-Callejo, Luis
AU - Solís, Martín
AU - Zorita-Lamadrid, Angel
AU - Duque-Pérez, Oscar
AU - Gonzalez-Morales, Luis
AU - García, Felix Santos
AU - Jaramillo-Duque, Alvaro
AU - Ospino-Castro, Adalberto
AU - Alonso-Gómez, Victor
AU - Bello, Hugo J.
N1 - Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2022/5/1
Y1 - 2022/5/1
N2 - Buildings are currently among the largest consumers of electrical energy with considerable increases in CO2 emissions in recent years. Although there have been notable advances in energy efficiency, buildings still have great untapped savings potential. Within demand-side management, some tools have helped improve electricity consumption, such as energy forecast models. However, because most forecasting models are not focused on updating based on the changing nature of buildings, they do not help exploit the savings potential of buildings. Considering the aforementioned, the objective of this article is to analyze the integration of methods that can help forecasting models to better adapt to the changes that occur in the behavior of buildings, ensuring that these can be used as tools to enhance savings in buildings. For this study, active and passive change detection methods were considered to be integrators in the decision tree and deep learning models. The results show that constant retraining for the decision tree models, integrating change detection methods, helped them to better adapt to changes in the whole building’s electrical consumption. However, for deep learning models, this was not the case, as constant retraining with small volumes of data only worsened their performance. These results may lead to the option of using tree decision models in buildings where electricity consumption is constantly changing.
AB - Buildings are currently among the largest consumers of electrical energy with considerable increases in CO2 emissions in recent years. Although there have been notable advances in energy efficiency, buildings still have great untapped savings potential. Within demand-side management, some tools have helped improve electricity consumption, such as energy forecast models. However, because most forecasting models are not focused on updating based on the changing nature of buildings, they do not help exploit the savings potential of buildings. Considering the aforementioned, the objective of this article is to analyze the integration of methods that can help forecasting models to better adapt to the changes that occur in the behavior of buildings, ensuring that these can be used as tools to enhance savings in buildings. For this study, active and passive change detection methods were considered to be integrators in the decision tree and deep learning models. The results show that constant retraining for the decision tree models, integrating change detection methods, helped them to better adapt to changes in the whole building’s electrical consumption. However, for deep learning models, this was not the case, as constant retraining with small volumes of data only worsened their performance. These results may lead to the option of using tree decision models in buildings where electricity consumption is constantly changing.
KW - drift detection
KW - electrical consumption forecasting
KW - energy forecasting
KW - machine learning
KW - smart buildings
UR - http://www.scopus.com/inward/record.url?scp=85130535884&partnerID=8YFLogxK
U2 - 10.3390/su14105857
DO - 10.3390/su14105857
M3 - Artículo
AN - SCOPUS:85130535884
SN - 2071-1050
VL - 14
JO - Sustainability (Switzerland)
JF - Sustainability (Switzerland)
IS - 10
M1 - 5857
ER -