Adaptive and Intelligent Edge Computing Based Building Energy Management System

Sergio Márquez-Sánchez; Sergio Alonso-Rollán; Francisco Pinto-Santos; Aiman Erbad; Muhammad Hanan Abdul Ibrar; Javier Hernandez Fernandez; Mahdi Houchati; Juan Manuel Corchado

doi:10.1007/978-3-031-36957-5_4

Adaptive and Intelligent Edge Computing Based Building Energy Management System

Sergio Márquez-Sánchez^*
, Sergio Alonso-Rollán
, Francisco Pinto-Santos
, Aiman Erbad
, Muhammad Hanan Abdul Ibrar
, Javier Hernandez Fernandez
, Mahdi Houchati
, Juan Manuel Corchado

^*Corresponding author for this work

CSE Information & Computing Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Most building and energy management system (BEMS) solutions follow a set of rules (supervised or unsupervised learning) to make energy-saving recommendations to inhabitants. However, these systems are normally solely trained on energy data meaning that they do not consider other key factors, such as the inhabitants’ comfort or preferences. The lack of adaption to inhabitants renders these energy-saving solutions largely ineffective. Moreover, BEMS solutions are cloud-based entailing greater cyberattack risks and a high data transmission load. To address these problems, this research proposes an edge computing architecture based on virtual organizations and distributed explainable artificial intelligence (XAI) algorithms for optimized energy use in buildings/homes and demand response. Thanks to virtual organizations’ energy efficiency (EE) measures, which consider the inhabitants’ comfort and dynamically learn from real-time inhabitant data, the consumption patterns of the inhabitants are effectively optimized.

Original language	English
Title of host publication	Trends in Sustainable Smart Cities and Territories
Editors	Luis Fernando Castillo Ossa, Gustavo Isaza, Óscar Cardona, Omar Danilo Castrillón, Juan Manuel Corchado Rodriguez, Fernando De la Prieta Pintado
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	37-48
Number of pages	12
ISBN (Print)	9783031369568
DOIs	https://doi.org/10.1007/978-3-031-36957-5_4
Publication status	Published - 2023
Event	2nd International Conference on Sustainable Smart Cities and Territories, SSCT 2023 - Manizales, Colombia Duration: 21 Jun 2023 → 23 Jun 2023

Publication series

Name	Lecture Notes in Networks and Systems
Volume	732 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	2nd International Conference on Sustainable Smart Cities and Territories, SSCT 2023
Country/Territory	Colombia
City	Manizales
Period	21/06/23 → 23/06/23

Keywords

Deep learning
Edge computing
Explainable AI
Social computing
Virtual organizations

Access to Document

10.1007/978-3-031-36957-5_4

Cite this

Márquez-Sánchez, S., Alonso-Rollán, S., Pinto-Santos, F., Erbad, A., Ibrar, M. H. A., Fernandez, J. H., Houchati, M., & Corchado, J. M. (2023). Adaptive and Intelligent Edge Computing Based Building Energy Management System. In L. F. Castillo Ossa, G. Isaza, Ó. Cardona, O. D. Castrillón, J. M. Corchado Rodriguez, & F. De la Prieta Pintado (Eds.), Trends in Sustainable Smart Cities and Territories (pp. 37-48). (Lecture Notes in Networks and Systems; Vol. 732 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-36957-5_4

Márquez-Sánchez, Sergio ; Alonso-Rollán, Sergio ; Pinto-Santos, Francisco et al. / Adaptive and Intelligent Edge Computing Based Building Energy Management System. Trends in Sustainable Smart Cities and Territories. editor / Luis Fernando Castillo Ossa ; Gustavo Isaza ; Óscar Cardona ; Omar Danilo Castrillón ; Juan Manuel Corchado Rodriguez ; Fernando De la Prieta Pintado. Springer Science and Business Media Deutschland GmbH, 2023. pp. 37-48 (Lecture Notes in Networks and Systems).

@inproceedings{c7c1f2a876f3406abb88bf0e0a22eaa6,

title = "Adaptive and Intelligent Edge Computing Based Building Energy Management System",

abstract = "Most building and energy management system (BEMS) solutions follow a set of rules (supervised or unsupervised learning) to make energy-saving recommendations to inhabitants. However, these systems are normally solely trained on energy data meaning that they do not consider other key factors, such as the inhabitants{\textquoteright} comfort or preferences. The lack of adaption to inhabitants renders these energy-saving solutions largely ineffective. Moreover, BEMS solutions are cloud-based entailing greater cyberattack risks and a high data transmission load. To address these problems, this research proposes an edge computing architecture based on virtual organizations and distributed explainable artificial intelligence (XAI) algorithms for optimized energy use in buildings/homes and demand response. Thanks to virtual organizations{\textquoteright} energy efficiency (EE) measures, which consider the inhabitants{\textquoteright} comfort and dynamically learn from real-time inhabitant data, the consumption patterns of the inhabitants are effectively optimized.",

keywords = "Deep learning, Edge computing, Explainable AI, Social computing, Virtual organizations",

author = "Sergio M{\'a}rquez-S{\'a}nchez and Sergio Alonso-Roll{\'a}n and Francisco Pinto-Santos and Aiman Erbad and Ibrar, \{Muhammad Hanan Abdul\} and Fernandez, \{Javier Hernandez\} and Mahdi Houchati and Corchado, \{Juan Manuel\}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 2nd International Conference on Sustainable Smart Cities and Territories, SSCT 2023 ; Conference date: 21-06-2023 Through 23-06-2023",

year = "2023",

doi = "10.1007/978-3-031-36957-5\_4",

language = "English",

isbn = "9783031369568",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "37--48",

editor = "\{Castillo Ossa\}, \{Luis Fernando\} and Gustavo Isaza and {\'O}scar Cardona and Castrill{\'o}n, \{Omar Danilo\} and \{Corchado Rodriguez\}, \{Juan Manuel\} and \{De la Prieta Pintado\}, Fernando",

booktitle = "Trends in Sustainable Smart Cities and Territories",

address = "Germany",

}

Márquez-Sánchez, S, Alonso-Rollán, S, Pinto-Santos, F, Erbad, A, Ibrar, MHA, Fernandez, JH, Houchati, M & Corchado, JM 2023, Adaptive and Intelligent Edge Computing Based Building Energy Management System. in LF Castillo Ossa, G Isaza, Ó Cardona, OD Castrillón, JM Corchado Rodriguez & F De la Prieta Pintado (eds), Trends in Sustainable Smart Cities and Territories. Lecture Notes in Networks and Systems, vol. 732 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 37-48, 2nd International Conference on Sustainable Smart Cities and Territories, SSCT 2023, Manizales, Colombia, 21/06/23. https://doi.org/10.1007/978-3-031-36957-5_4

Adaptive and Intelligent Edge Computing Based Building Energy Management System. / Márquez-Sánchez, Sergio; Alonso-Rollán, Sergio; Pinto-Santos, Francisco et al.
Trends in Sustainable Smart Cities and Territories. ed. / Luis Fernando Castillo Ossa; Gustavo Isaza; Óscar Cardona; Omar Danilo Castrillón; Juan Manuel Corchado Rodriguez; Fernando De la Prieta Pintado. Springer Science and Business Media Deutschland GmbH, 2023. p. 37-48 (Lecture Notes in Networks and Systems; Vol. 732 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Adaptive and Intelligent Edge Computing Based Building Energy Management System

AU - Márquez-Sánchez, Sergio

AU - Alonso-Rollán, Sergio

AU - Pinto-Santos, Francisco

AU - Erbad, Aiman

AU - Ibrar, Muhammad Hanan Abdul

AU - Fernandez, Javier Hernandez

AU - Houchati, Mahdi

AU - Corchado, Juan Manuel

PY - 2023

Y1 - 2023

N2 - Most building and energy management system (BEMS) solutions follow a set of rules (supervised or unsupervised learning) to make energy-saving recommendations to inhabitants. However, these systems are normally solely trained on energy data meaning that they do not consider other key factors, such as the inhabitants’ comfort or preferences. The lack of adaption to inhabitants renders these energy-saving solutions largely ineffective. Moreover, BEMS solutions are cloud-based entailing greater cyberattack risks and a high data transmission load. To address these problems, this research proposes an edge computing architecture based on virtual organizations and distributed explainable artificial intelligence (XAI) algorithms for optimized energy use in buildings/homes and demand response. Thanks to virtual organizations’ energy efficiency (EE) measures, which consider the inhabitants’ comfort and dynamically learn from real-time inhabitant data, the consumption patterns of the inhabitants are effectively optimized.

AB - Most building and energy management system (BEMS) solutions follow a set of rules (supervised or unsupervised learning) to make energy-saving recommendations to inhabitants. However, these systems are normally solely trained on energy data meaning that they do not consider other key factors, such as the inhabitants’ comfort or preferences. The lack of adaption to inhabitants renders these energy-saving solutions largely ineffective. Moreover, BEMS solutions are cloud-based entailing greater cyberattack risks and a high data transmission load. To address these problems, this research proposes an edge computing architecture based on virtual organizations and distributed explainable artificial intelligence (XAI) algorithms for optimized energy use in buildings/homes and demand response. Thanks to virtual organizations’ energy efficiency (EE) measures, which consider the inhabitants’ comfort and dynamically learn from real-time inhabitant data, the consumption patterns of the inhabitants are effectively optimized.

KW - Deep learning

KW - Edge computing

KW - Explainable AI

KW - Social computing

KW - Virtual organizations

UR - https://www.scopus.com/pages/publications/85172199426

U2 - 10.1007/978-3-031-36957-5_4

DO - 10.1007/978-3-031-36957-5_4

M3 - Conference contribution

AN - SCOPUS:85172199426

SN - 9783031369568

T3 - Lecture Notes in Networks and Systems

SP - 37

EP - 48

BT - Trends in Sustainable Smart Cities and Territories

A2 - Castillo Ossa, Luis Fernando

A2 - Isaza, Gustavo

A2 - Cardona, Óscar

A2 - Castrillón, Omar Danilo

A2 - Corchado Rodriguez, Juan Manuel

A2 - De la Prieta Pintado, Fernando

PB - Springer Science and Business Media Deutschland GmbH

T2 - 2nd International Conference on Sustainable Smart Cities and Territories, SSCT 2023

Y2 - 21 June 2023 through 23 June 2023

ER -

Márquez-Sánchez S, Alonso-Rollán S, Pinto-Santos F, Erbad A, Ibrar MHA, Fernandez JH et al. Adaptive and Intelligent Edge Computing Based Building Energy Management System. In Castillo Ossa LF, Isaza G, Cardona Ó, Castrillón OD, Corchado Rodriguez JM, De la Prieta Pintado F, editors, Trends in Sustainable Smart Cities and Territories. Springer Science and Business Media Deutschland GmbH. 2023. p. 37-48. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-36957-5_4

Adaptive and Intelligent Edge Computing Based Building Energy Management System

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

EX-QNRF-NPRPS-42: Adaptive and Intelligent Edge Computing Based Building Energy Management System (AI-BEMS)

Cite this

Adaptive and Intelligent Edge Computing Based Building Energy Management System

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

EX-QNRF-NPRPS-42: Adaptive and Intelligent Edge Computing Based Building Energy Management System (AI-BEMS)

Cite this