Thermal Load Predictions in Low-Energy Buildings: A Hybrid AI-Based Approach Integrating Integral Feature Selection and Machine Learning Models

Guardado en:

Bibliografiske detaljer
Udgivet i:	Applied Sciences vol. 15, no. 11 (2025), p. 6348
Hovedforfatter:	Youness, El Mghouchi
Andre forfattere:	Udristioiu Mihaela Tinca
Udgivet:	MDPI AG
Fag:	Morocco Machine learning Software Accuracy Green buildings Datasets Cooling Artificial intelligence Generalized linear models Optimization Neural networks Computer simulation Feature selection Architecture Energy efficiency Heat HVAC Algorithms Emission standards Energy consumption Climate Case studies
Online adgang:	Citation/Abstract Full Text + Graphics Full Text - PDF
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!

Beskrivelse
Resumen:	A hybrid Artificial Intelligence (AI) framework centered on metamodeling, integrating simulation data with hybrid data-driven techniques, was implemented to enhance the predictive accuracy and optimization of thermal load projections in three distinct climates in Morocco. Initially, 13 machine learning (ML) models were assessed to predict heating and cooling loads. The best-performing models from this stage were then selected for the subsequent phase to find out the optimal combinations of inputs to predict thermal loads. In this phase, an Integral Feature Selection (IFS) method was employed in conjunction with the best ML models. An extensive evaluation using advanced statistical measures was performed during the evaluation stage. The results reveal that, for each climate, numerous high-accuracy prediction pathways were identified for thermal load prediction, surpassing the confidence level of 99% for R2. The results found here outperformed those reported by other researchers in thermal load predictions for Low-Energy Buildings (LEBs).
ISSN:	2076-3417
DOI:	10.3390/app15116348
Fuente:	Publicly Available Content Database