The evaluation of the energy performance of existing or new buildings is a fundamental action to guarantee the feasibility of a project and the achievement of the minimum efficiency requirements. In general, the determination of the thermal loads of a building is carried out via software but their use requires adequate knowledge of physical phenomena and therefore the presence of an expert user. Furthermore, the resolution can be difficult to implement and can require high computational costs; all conditions that can influence the success of a project. Based on these considerations, this work proposes an alternative solution to traditional calculation tools, which in a simple and effective way, highly reliable and with low computational times, solves the complex problem of the heat balance of a building. The authors explore the possibility of using artificial neural networks for the development of a decision support tool, which, through the identification of a few and fundamental input data, simultaneously determines and predicts the heating and cooling loads of buildings. Through the case study of the Italian non-residential building stock, the networks were explored and validated by an in-depth error analysis and a selection of the most suitable variables was conducted by Pearson's analysis. In this way, knowing only a few well-known data, the instrument immediately determines the total thermal loads and can be easily accessed by any user; its high reliability is demonstrated by the performance analysis results according to the criteria and error indices evaluated by ASHRAE Guideline 14.

D'Amico A., Ciulla G. (2022). An intelligent way to predict the building thermal needs: ANNs and optimization. EXPERT SYSTEMS WITH APPLICATIONS, 191 [10.1016/j.eswa.2021.116293].

An intelligent way to predict the building thermal needs: ANNs and optimization

D'Amico A.
Primo
Writing – Original Draft Preparation
;
Ciulla G.
Secondo
Writing – Review & Editing
2022-04-01

Abstract

The evaluation of the energy performance of existing or new buildings is a fundamental action to guarantee the feasibility of a project and the achievement of the minimum efficiency requirements. In general, the determination of the thermal loads of a building is carried out via software but their use requires adequate knowledge of physical phenomena and therefore the presence of an expert user. Furthermore, the resolution can be difficult to implement and can require high computational costs; all conditions that can influence the success of a project. Based on these considerations, this work proposes an alternative solution to traditional calculation tools, which in a simple and effective way, highly reliable and with low computational times, solves the complex problem of the heat balance of a building. The authors explore the possibility of using artificial neural networks for the development of a decision support tool, which, through the identification of a few and fundamental input data, simultaneously determines and predicts the heating and cooling loads of buildings. Through the case study of the Italian non-residential building stock, the networks were explored and validated by an in-depth error analysis and a selection of the most suitable variables was conducted by Pearson's analysis. In this way, knowing only a few well-known data, the instrument immediately determines the total thermal loads and can be easily accessed by any user; its high reliability is demonstrated by the performance analysis results according to the criteria and error indices evaluated by ASHRAE Guideline 14.
1-apr-2022
Settore ING-IND/11 - Fisica Tecnica Ambientale
D'Amico A., Ciulla G. (2022). An intelligent way to predict the building thermal needs: ANNs and optimization. EXPERT SYSTEMS WITH APPLICATIONS, 191 [10.1016/j.eswa.2021.116293].
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0957417421015980-main.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 2.6 MB
Formato Adobe PDF
2.6 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/590238
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 5
social impact