Data-driven framework for energy optimizing net-zero energy buildings (NZEB): A functional assessment of energy efficiency and thermal comfort

Mohammed A. Alghassab

Energy, 2025, vol. 330, issue C

Abstract: This study presents a comprehensive AI-driven framework for evaluating energy consumption and optimizing the performance of Net-Zero Energy Buildings (NZEB) in contrasting climates. Focusing on Riyadh, Saudi Arabia, and Lhasa, China, Long Short-Term Memory (LSTM) networks were utilized to predict energy consumption patterns in educational and office buildings. The model achieved a mean absolute percentage error (MAPE) of 0.81 %–4.85 % in energy consumption predictions and an error range of 0.65 %–2.41 % for thermal comfort predictions. Sensitivity analysis revealed that a 10 % reduction in cooling demand could result in up to a 7.2 % decrease in operational costs. Furthermore, the economic analysis indicated that implementing data-driven energy efficiency measures could lead to a 12.5 % reduction in greenhouse gas emissions. Policy implications were also addressed, showing that integrating these models into urban planning could enhance resource management by 15 %, fostering sustainable urban growth. Sensitivity analysis revealed that climatic parameters and mechanical ventilation had the most significant impact on energy consumption. Furthermore, the economic model indicated that initial investments in energy optimization technologies resulted in a substantial return on investment (ROI) over 10 years, with an average ROI of 185 %. Probabilistic distribution analysis showed distinct energy consumption patterns between educational and office buildings, underscoring the need for tailored energy management strategies.

Keywords: Net-zero energy building; Educational; Official; Deep learning framework; Long short-term memory; Environmental resilience (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225024764
Full text for ScienceDirect subscribers only

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:eee:energy:v:330:y:2025:i:c:s0360544225024764

DOI: 10.1016/j.energy.2025.136834

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().