Advancing Sustainable Energy Management: A Comprehensive Review of Artificial Intelligence Techniques in Building | ||||
| Engineering Research Journal (Shoubra) | ||||
| Volume 53, Issue 2, April 2024, Page 26-46 PDF (1.38 MB) | ||||
| Document Type: Review Articles | ||||
| DOI: 10.21608/erjsh.2023.226854.1196 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Ahmed M. Hanafi   1; Mohamed Ahmed Moawed2; Osama Ezzat Abdellatif 2
| ||||
| 1Department of Mechatronics Engineering, Faculty of Engineering, October 6 University, Giza, Egypt. | ||||
| 2Department of Mechanical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo, Egypt | ||||
| Abstract | ||||
| This paper explores artificial intelligence's (AI) transformative potential in optimizing energy management within buildings, aligning with environmental objectives and sustainable practices. AI-based methodologies are pivotal in identifying inefficiencies, forecasting future energy requirements, and mitigating energy wastage. Adopting AI-driven energy management systems enhances efficiency, reduces costs, and contributes to a decreased building environmental footprint. Furthermore, AI empowers buildings to actively participate in energy markets by accurately predicting real-time supply and demand without operational disruption. The study delves into various AI applications, including energy prediction, optimization, fault detection and diagnosis (FDD), and real-world implementations. Notably, AI's role in fault detection and diagnostics is highlighted, emphasizing its substantial contribution to diagnostic precision. Specific numerical outcomes from reviewed studies underscore the tangible impact of AI techniques. Predictive control powered by AI achieved a remarkable 20% reduction in heating energy without compromising comfort. Additionally, smart home energy management algorithms demonstrated a notable 22.63% decrease in electricity costs and a 22.77% reduction in the peak-to-average ratio. These concrete figures underscore the practical success of AI techniques in significantly reducing energy consumption. This review affirms the transformative potential of AI in building energy management. Including specific numerical values from empirical studies adds a quantitative dimension to the discussion, providing clear evidence of the positive impact of AI on energy efficiency. | ||||
| Keywords | ||||
| Prediction Models; Control Strategies; Optimization Energy Efficiency; Fault Detection; Building Performance | ||||
|
Statistics Article View: 143 PDF Download: 200 |
||||
