A Demand Forecasting Strategy Based on a Retrofit Architecture for Remote Monitoring of Legacy Building Circuits

Rubens A. Fernandes (), Raimundo C. S. Gomes, Carlos T. Costa, Celso Carvalho, Neilson L. Vilaça, Lennon B. F. Nascimento, Fabricio R. Seppe, Israel G. Torné and Heitor L. N. da Silva
Additional contact information
Rubens A. Fernandes: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil
Raimundo C. S. Gomes: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil
Carlos T. Costa: Programa de Pós-Graduação em Engenharia Elétrica—PPGEE, Federal University of Pará, Belém 66075-110, Brazil
Celso Carvalho: Departamento de Eletrônica e Computação—DTEC, Federal University of Amazonas, Manaus 69067-005, Brazil
Neilson L. Vilaça: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil
Lennon B. F. Nascimento: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil
Fabricio R. Seppe: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil
Israel G. Torné: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil
Heitor L. N. da Silva: Embedded Systems Laboratory, State University of Amazonas, Manaus 69050-020, Brazil

Sustainability, 2023, vol. 15, issue 14, 1-37

Abstract: Energy demand forecasting is crucial for planning and optimizing the use of energy resources in building facilities. However, integrating digital solutions and learning techniques into legacy buildings presents significant challenges due to limited or outdated resources, hampering predictive analytics in these buildings and their circuits. To fill this gap, this article proposes an innovative demand forecasting strategy using an AIoT retrofit architecture based on the SmartLVGrid metamodel. This architecture allows remote monitoring of legacy building circuits, facilitating the collection, processing and storage of data in the cloud. We use several learning algorithms, including linear regression, support vector regressor, random forest regressor, XGBoost regressor, and long short-term memory (LSTM) neural network, to predict energy demand 15 min ahead, identifying potential overruns of contracted demand in accordance with Brazilian regulations. After Bayesian optimization, the LSTM neural network outperformed other models for most of the selected datasets and detected 32 out of 38 demand overruns on the test set. XGBoost and random forest followed closely, detecting 30 demand overruns. Overall, our cost-effective solution optimizes energy usage and efficiently mitigates potential demand exceedances in building installations. This is achieved through a step-by-step approach to upgrading existing aging facilities, which promotes energy efficiency and sustainability.

Keywords: demand forecast; retrofit; SmartLVGrid; AIoT; machine learning; real-time energy monitoring; energy efficiency; sustainability; smart buildings (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/14/11161/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/14/11161/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:14:p:11161-:d:1196262

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().