Loading...
Applications of Explainable Artificial Intelligence (XAI) and interpretable Artificial Intelligence (AI) in smart buildings and energy savings in buildings : A systematic review
Haghighat, Mohammadreza MohammadiSavadkoohi, Ehsan Shafiabady, Niusha
Haghighat, Mohammadreza
MohammadiSavadkoohi, Ehsan
Shafiabady, Niusha
Abstract
This study systematically reviews the applications of XAI and Interpretable AI in smart buildings, focusing on energy efficiency and management. With buildings accounting for a significant portion of global energy consumption, the integration of AI-driven solutions has emerged as a key strategy for optimizing energy use. However, the lack of transparency in AI models presents a challenge for adoption and trust. This review addresses this gap by analyzing 32 research papers that explore various AI techniques in predictive modeling, energy monitoring, fault detection, and optimization strategies. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology was employed to identify, assess, and categorize relevant studies. Key findings highlight the role of XAI and Interpretable AI in improving energy forecasting accuracy, enhancing decision-making processes, and increasing model interpretability for end-users. The results suggest that AI-driven energy management systems can significantly contribute to sustainability by reducing energy waste and improving operational efficiency in smart buildings. Additionally, the study identifies research gaps and proposes future directions, such as integrating real-world data, refining interpretability techniques, and expanding AI applications across diverse building types. This research provides valuable insights for academia, industry, and policymakers seeking to implement transparent and effective AI-driven energy management solutions in smart buildings. The novelty of this review lies in its structured analysis of XAI’s role in enhancing the explainability and reliability of AI applications in building energy management, setting the foundation for future advancements in the field.
Keywords
Explainable Artificial Intelligence (XAI), interpretable AI, smart buildings, energy savings, energy consumption
Date
2025
Type
Journal article
Journal
Journal of Building Engineering
Book
Volume
107
Issue
Page Range
1-34
Article Number
Article 112542
ACU Department
Peter Faber Business School
Faculty of Law and Business
Faculty of Law and Business
Collections
Relation URI
Source URL
Event URL
Open Access Status
License
All rights reserved
File Access
Controlled
Notes
© 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.