Comparative study of continuous hourly energy consumption forecasting strategies with small data sets to support demand management decisions in buildings

Mariano-Hernández, Deyslen; Hernández-Callejo, Luís; Solís, Martín; Zorita-Lamadrid, Ángel L.; Duque-Pérez, Óscar; González, L.G.; Alonso‐Gómez, Víctor; Jaramillo-Duque, Álvaro; García, Félix Santos

doi:10.1002/ese3.1298

Cited by 3 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the investigations that concluded with the research paper [42,44], it was possible to accomplish the PO3, which consisted in the develop an energy consumption forecasting methodology that allows energy consumption to be estimated using a multi-step direct forecasting strategy.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Demand forecasting model for load shifting strategy in building energy management system

Hernández¹

View full text Add to dashboard Cite

Among the sectors with the highest energy consumption are transport, industries, and buildings.Buildings are responsible for the third part of energy consumption and almost 40% of CO2 emissions worldwide. The search to improve the comfort of the occupants inside the buildings has brought a consequence that buildings are increasingly equipped with devices that help to improve the thermal comfort, visual comfort, and air quality inside the buildings, causing more energy demand regardless of the type of building making buildings an untapped efficiency potential. This doctoral thesis presents a model for forecasting electricity demand in buildings based on machine learning for load-shifting strategies, which can be implemented in building energy management systems. The forecast model developed allows forecasting the electricity demand for the next 24 hours starting at any time of the day. To achieve this forecast, not only electricity consumption was considered, but also climatic variables, calendar variables, and past time values. Different types of machine learning algorithms were compared using performance measures resulting in tree decision and deep learning algorithms performing better with the developed model.

show abstract

Section: Resultsmentioning

confidence: 99%

“…From the research paper [44], which consisted of the comparison between the decision tree algorithm and deep learning algorithm using different multi-step forecasting methods with limited time series data, the following results were obtained:…”

Section: Resultsmentioning

confidence: 99%

Demand forecasting model for load shifting strategy in building energy management system

Hernández¹

View full text Add to dashboard Cite

show abstract

Exploring cost-effective strategies for emission reduction of public buildings in a life-cycle

Huang

Wang

et al. 2023

Energy and Buildings

View full text Add to dashboard Cite

Predicting Commercial Building Energy Consumption Using a Multivariate Multilayered Long-Short Term Memory Time-Series Model

et al. 2023

View full text Add to dashboard Cite

The global demand for energy has been steadily increasing due to population growth, urbanization, and industrialization. Numerous researchers worldwide are striving to create precise forecasting models for predicting energy consumption to manage supply and demand effectively. In this research, a time-series forecasting model based on multivariate multilayered long short-term memory (LSTM) is proposed for forecasting energy consumption and tested using data obtained from commercial buildings in Melbourne, Australia: the Advanced Technologies Center, Advanced Manufacturing and Design Center, and Knox Innovation, Opportunity, and Sustainability Center buildings. This research specifically identifies the best forecasting method for subtropical conditions and evaluates its performance by comparing it with the most commonly used methods at present, including LSTM, bidirectional LSTM, and linear regression. The proposed multivariate, multilayered LSTM model was assessed by comparing mean average error (MAE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE) values with and without labeled time. Results indicate that the proposed model exhibits optimal performance with improved precision and accuracy. Specifically, the proposed LSTM model achieved a decrease in MAE of 30%, RMSE of 25%, and MAPE of 20% compared with the LSTM method. Moreover, it outperformed the bidirectional LSTM method with a reduction in MAE of 10%, RMSE of 20%, and MAPE of 18%. Furthermore, the proposed model surpassed linear regression with a decrease in MAE by 2%, RMSE by 7%, and MAPE by 10%.These findings highlight the significant performance increase achieved by the proposed multivariate multilayered LSTM model in energy consumption forecasting.

show abstract

Comparative study of continuous hourly energy consumption forecasting strategies with small data sets to support demand management decisions in buildings

Cited by 3 publications

References 35 publications

Demand forecasting model for load shifting strategy in building energy management system

Demand forecasting model for load shifting strategy in building energy management system

Exploring cost-effective strategies for emission reduction of public buildings in a life-cycle

Predicting Commercial Building Energy Consumption Using a Multivariate Multilayered Long-Short Term Memory Time-Series Model

Contact Info

Product

Resources

About