An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings

Muhammad Ibrar; Hayla Nahom; Abegaz Mohammed; Sergio Márquez-Sánchez; Javier Hernandez Fernandez; Juan Manuel Corchado; Aiman Erbad

doi:10.1007/978-3-031-82073-1_9

An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings

Muhammad Ibrar
, Hayla Nahom
, Abegaz Mohammed
, Sergio Márquez-Sánchez
, Javier Hernandez Fernandez
, Juan Manuel Corchado
, Aiman Erbad^*

^*Corresponding author for this work

Universidad de Salamanca
Iberdrola Innovation Middle East
Qatar University

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

Abstract

Smart building energy demand response (DR) plays a paramount role in the decarbonization of energy use by leveraging different techniques that adjust energy consumption in response to fluctuating prices and demands. In this paper, we present an explainable AI-integrated DR optimization framework for smart buildings. This adaptive XAI-based DR approach intelligently forecasts energy demands and schedules the energy consumption of the buildings based on the forecasted demand patterns, grid conditions, and energy prices. This approach allows the stakeholders to make informed and optimal DR decisions based on the forecasted demand to maximize energy efficiency and user comfort while minimizing electricity costs. The simulation results demonstrate that the proposed approach promotes energy efficiency and user comfort .

Original language	English
Title of host publication	Distributed Computing and Artificial Intelligence, 21st International Conference -
Editors	R Chinthaginjala, P Sitek, N Min-Allah, K Matsui, S Ossowski, S Rodriguez
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	88-98
Number of pages	11
Volume	1259
ISBN (Electronic)	978-3-031-82073-1
ISBN (Print)	9783031820724
DOIs	https://doi.org/10.1007/978-3-031-82073-1_9
Publication status	Published - Feb 2025
Event	21st International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2024 - Salamanca, Spain Duration: 25 Jun 2024 → 27 Jun 2024

Publication series

Name	Lecture Notes In Networks And Systems

Conference

Conference	21st International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2024
Country/Territory	Spain
City	Salamanca
Period	25/06/24 → 27/06/24

Keywords

Demand response optimization
Energy management
Explainable artificial intelligence
K-means
Random forest regressor

Access to Document

10.1007/978-3-031-82073-1_9

Cite this

Ibrar, M., Nahom, H., Mohammed, A., Márquez-Sánchez, S., Fernandez, J. H., Corchado, J. M., & Erbad, A. (2025). An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings. In R. Chinthaginjala, P. Sitek, N. Min-Allah, K. Matsui, S. Ossowski, & S. Rodriguez (Eds.), Distributed Computing and Artificial Intelligence, 21st International Conference - (Vol. 1259, pp. 88-98). (Lecture Notes In Networks And Systems). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-82073-1_9

Ibrar, Muhammad ; Nahom, Hayla ; Mohammed, Abegaz et al. / An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings. Distributed Computing and Artificial Intelligence, 21st International Conference - . editor / R Chinthaginjala ; P Sitek ; N Min-Allah ; K Matsui ; S Ossowski ; S Rodriguez. Vol. 1259 Springer Science and Business Media Deutschland GmbH, 2025. pp. 88-98 (Lecture Notes In Networks And Systems).

@inproceedings{6095adfc46dd432ba96b0186eb0a0814,

title = "An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings",

abstract = "Smart building energy demand response (DR) plays a paramount role in the decarbonization of energy use by leveraging different techniques that adjust energy consumption in response to fluctuating prices and demands. In this paper, we present an explainable AI-integrated DR optimization framework for smart buildings. This adaptive XAI-based DR approach intelligently forecasts energy demands and schedules the energy consumption of the buildings based on the forecasted demand patterns, grid conditions, and energy prices. This approach allows the stakeholders to make informed and optimal DR decisions based on the forecasted demand to maximize energy efficiency and user comfort while minimizing electricity costs. The simulation results demonstrate that the proposed approach promotes energy efficiency and user comfort .",

keywords = "Demand response optimization, Energy management, Explainable artificial intelligence, K-means, Random forest regressor",

author = "Muhammad Ibrar and Hayla Nahom and Abegaz Mohammed and Sergio M{\'a}rquez-S{\'a}nchez and Fernandez, \{Javier Hernandez\} and Corchado, \{Juan Manuel\} and Aiman Erbad",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 21st International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2024 ; Conference date: 25-06-2024 Through 27-06-2024",

year = "2025",

month = feb,

doi = "10.1007/978-3-031-82073-1\_9",

language = "English",

isbn = "9783031820724",

volume = "1259",

series = "Lecture Notes In Networks And Systems",

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

pages = "88--98",

editor = "R Chinthaginjala and P Sitek and N Min-Allah and K Matsui and S Ossowski and S Rodriguez",

booktitle = "Distributed Computing and Artificial Intelligence, 21st International Conference -",

address = "Germany",

}

Ibrar, M, Nahom, H, Mohammed, A, Márquez-Sánchez, S, Fernandez, JH, Corchado, JM & Erbad, A 2025, An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings. in R Chinthaginjala, P Sitek, N Min-Allah, K Matsui, S Ossowski & S Rodriguez (eds), Distributed Computing and Artificial Intelligence, 21st International Conference - . vol. 1259, Lecture Notes In Networks And Systems, Springer Science and Business Media Deutschland GmbH, pp. 88-98, 21st International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2024, Salamanca, Spain, 25/06/24. https://doi.org/10.1007/978-3-031-82073-1_9

An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings. / Ibrar, Muhammad; Nahom, Hayla; Mohammed, Abegaz et al.
Distributed Computing and Artificial Intelligence, 21st International Conference - . ed. / R Chinthaginjala; P Sitek; N Min-Allah; K Matsui; S Ossowski; S Rodriguez. Vol. 1259 Springer Science and Business Media Deutschland GmbH, 2025. p. 88-98 (Lecture Notes In Networks And Systems).

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

TY - GEN

T1 - An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings

AU - Ibrar, Muhammad

AU - Nahom, Hayla

AU - Mohammed, Abegaz

AU - Márquez-Sánchez, Sergio

AU - Fernandez, Javier Hernandez

AU - Corchado, Juan Manuel

AU - Erbad, Aiman

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025/2

Y1 - 2025/2

N2 - Smart building energy demand response (DR) plays a paramount role in the decarbonization of energy use by leveraging different techniques that adjust energy consumption in response to fluctuating prices and demands. In this paper, we present an explainable AI-integrated DR optimization framework for smart buildings. This adaptive XAI-based DR approach intelligently forecasts energy demands and schedules the energy consumption of the buildings based on the forecasted demand patterns, grid conditions, and energy prices. This approach allows the stakeholders to make informed and optimal DR decisions based on the forecasted demand to maximize energy efficiency and user comfort while minimizing electricity costs. The simulation results demonstrate that the proposed approach promotes energy efficiency and user comfort .

AB - Smart building energy demand response (DR) plays a paramount role in the decarbonization of energy use by leveraging different techniques that adjust energy consumption in response to fluctuating prices and demands. In this paper, we present an explainable AI-integrated DR optimization framework for smart buildings. This adaptive XAI-based DR approach intelligently forecasts energy demands and schedules the energy consumption of the buildings based on the forecasted demand patterns, grid conditions, and energy prices. This approach allows the stakeholders to make informed and optimal DR decisions based on the forecasted demand to maximize energy efficiency and user comfort while minimizing electricity costs. The simulation results demonstrate that the proposed approach promotes energy efficiency and user comfort .

KW - Demand response optimization

KW - Energy management

KW - Explainable artificial intelligence

KW - K-means

KW - Random forest regressor

UR - https://www.scopus.com/pages/publications/85218938119

U2 - 10.1007/978-3-031-82073-1_9

DO - 10.1007/978-3-031-82073-1_9

M3 - Conference contribution

AN - SCOPUS:85218938119

SN - 9783031820724

VL - 1259

T3 - Lecture Notes In Networks And Systems

SP - 88

EP - 98

BT - Distributed Computing and Artificial Intelligence, 21st International Conference -

A2 - Chinthaginjala, R

A2 - Sitek, P

A2 - Min-Allah, N

A2 - Matsui, K

A2 - Ossowski, S

A2 - Rodriguez, S

PB - Springer Science and Business Media Deutschland GmbH

T2 - 21st International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2024

Y2 - 25 June 2024 through 27 June 2024

ER -

Ibrar M, Nahom H, Mohammed A, Márquez-Sánchez S, Fernandez JH, Corchado JM et al. An Explainable AI-Based Demand Response Optimization Framework for Smart Buildings. In Chinthaginjala R, Sitek P, Min-Allah N, Matsui K, Ossowski S, Rodriguez S, editors, Distributed Computing and Artificial Intelligence, 21st International Conference - . Vol. 1259. Springer Science and Business Media Deutschland GmbH. 2025. p. 88-98. (Lecture Notes In Networks And Systems). doi: 10.1007/978-3-031-82073-1_9