Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Optimizing sustainable building retrofits with Emperor Penguin Optimization: a machine-learning approach for energy consumption prediction
In the growing area of building sustainability, retrofitting methods are vital for energy efficiency and consumption reduction. This research examined retrofit measures’ potential for transformation, focusing on energy use. We used descriptive analysis, rigorous statistical testing, and cutting-edge machine learning to assess this phenomenon’s impact. The research method relied on strict data split into pre- and post-retrofit periods—the retrofit installation date defined this segmentation. Descriptive analysis showed that retrofitting reduced mean power use significantly. A thorough t test validated the statistical significance of the stated energy usage reduction. Our primary invention is machine-learning models, notably the feed forward neural network (FNN) and its upgraded version using the Emperor Penguin Optimizer (FNN-EPO). Comparing their prediction abilities showed that the FNN-EPO model performed better. Drawing on pre-retrofit data trends, our model effectively predicted post-retrofit energy use. Our research shows that retrofit measures reduce power use, underlining the need for data-driven analysis to evaluate them. The report emphasizes machine learning’s potential to alter this sector and provides a foundation for future research. This phenomenon has far-reaching effects, indicating that machine learning will be essential to sustainable retrofitting, intervention optimization, and energy-efficient building as global sustainability efforts increase.
Optimizing sustainable building retrofits with Emperor Penguin Optimization: a machine-learning approach for energy consumption prediction
In the growing area of building sustainability, retrofitting methods are vital for energy efficiency and consumption reduction. This research examined retrofit measures’ potential for transformation, focusing on energy use. We used descriptive analysis, rigorous statistical testing, and cutting-edge machine learning to assess this phenomenon’s impact. The research method relied on strict data split into pre- and post-retrofit periods—the retrofit installation date defined this segmentation. Descriptive analysis showed that retrofitting reduced mean power use significantly. A thorough t test validated the statistical significance of the stated energy usage reduction. Our primary invention is machine-learning models, notably the feed forward neural network (FNN) and its upgraded version using the Emperor Penguin Optimizer (FNN-EPO). Comparing their prediction abilities showed that the FNN-EPO model performed better. Drawing on pre-retrofit data trends, our model effectively predicted post-retrofit energy use. Our research shows that retrofit measures reduce power use, underlining the need for data-driven analysis to evaluate them. The report emphasizes machine learning’s potential to alter this sector and provides a foundation for future research. This phenomenon has far-reaching effects, indicating that machine learning will be essential to sustainable retrofitting, intervention optimization, and energy-efficient building as global sustainability efforts increase.
Optimizing sustainable building retrofits with Emperor Penguin Optimization: a machine-learning approach for energy consumption prediction
Asian J Civ Eng
Shihadeh, Jumana (Autor:in) / Abu-shaikha, Ma’in (Autor:in) / Zghoul, Nusaiba (Autor:in)
Asian Journal of Civil Engineering ; 25 ; 3379-3394
01.06.2024
16 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Lighting retrofits cut energy consumption
Online Contents | 1994
| British Library Online Contents | 2009