AI in Smart Building Energy Management: A Comprehensive Review of Power Monitoring and Control Systems
Journal of Intelligent Decision Making and Information Science · 09.09.2026 · 3 (18s) · 2221-2248
DOI: 10.17762/jidmis.v3.5981 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 09.09.2026. Verfasst von Yasir Muhialdain Khudhur. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid transition toward smart buildings and grid-interactive energy ecosystems has positioned artificial intelligence (AI) as a fundamental enabler of intelligent power monitoring and control. Buildings account for approximately 40% of global primary energy consumption and 36% of CO₂ emissions, making AI-driven optimization critical for decarbonization. AI-driven Energy Management Systems (EMS) integrate heterogeneous IoT sensing, smart metering, machine learning, deep learning, and real-time optimization strategies across a multilayered edge-fog-cloud architecture to achieve scalable and sustainable energy operation. Deployed models — including LSTM, CNN-LSTM hybrids, and deep reinforcement learning controllers — enable day-ahead demand forecasting with reported MAPE values as low as 1.2–3.5%, and adaptive HVAC and lighting control yielding 20–50% energy savings relative to conventional rule-based systems. These systems further support distributed renewable integration via PV forecasting, BESS scheduling, and V2G coordination, while edge inference over platforms such as ESP32 and NVIDIA Jetson reduces control latency below 10 ms. Hybrid AI frameworks combining physics-informed and data-driven models, alongside cybersecurity-aware architectures employing encrypted MQTT and anomaly detection, strengthen system reliability and privacy. Despite these advances, challenges in explainability, BACnet/Modbus interoperability, and standardized KPI benchmarking remain unresolved. This review consolidates current methodologies and outlines future directions including federated learning, XAI, and digital twin-based commissioning toward secure, interoperable smart-building ecosystems.
Zitieren
APA
Khudhur, Y. M. (2026). AI in Smart Building Energy Management: A Comprehensive Review of Power Monitoring and Control Systems. Journal of Intelligent Decision Making and Information Science, 3(18s), 2221-2248. https://doi.org/10.17762/jidmis.v3.5981
Vancouver
Khudhur YM. AI in Smart Building Energy Management: A Comprehensive Review of Power Monitoring and Control Systems. Journal of Intelligent Decision Making and Information Science. 2026;3(18s):2221-2248. doi:10.17762/jidmis.v3.5981
BibTeX
@article{Khudhur2026,
author = {Khudhur, Yasir Muhialdain},
title = {AI in Smart Building Energy Management: A Comprehensive Review of Power Monitoring and Control Systems},
journal = {Journal of Intelligent Decision Making and Information Science},
year = {2026},
volume = {3},
number = {18s},
pages = {2221--2248},
doi = {10.17762/jidmis.v3.5981}
}
EUVIMED