Life Cycle Sustainability Assessment (LCSA) in the built environment has increasingly drawn researchers’ attention in the preceding years; however, the lack of an integrated LCSA based model is still a barrier for its effective implementation into the building design process. This paper proposes a new comprehensive LCSA model to be integrated into the design process of new buildings and energy refurbishment scenarios of existing ones. The proposed model consists of sets of mathematic equations to describe LCSA pillars of buildings, including Life Cycle Assessment (LCA), Life Cycle Costing (LCC), and Social Life Cycle Assessment (SLCA) as the intermediate indices. A final LCSA index is then provided to describe a design scenario's performance from an LCSA perspective using the authors' new formulation and weighting method. The model is also integrated into the optimization process and enhanced with Machine Learning (ML) methods to accelerate the design-assessment process while preserving its accuracy. Finally, given the transition towards buildings' electrification by Renewable Energy Sources (RESs), as a supportive technology, the size-optimization of a residential building's short-term thermal and electrical Energy Storage Systems (ESSs) is chosen to demonstrate the model's capabilities. For this purpose, the building case study is parametrically modeled in Grasshopper, Energy plus, and Matlab for energy analysis, data processing, and machine learning.

A novel LCSA-Machine learning based optimization model for sustainable building design-A case study of energy storage systems

Amini Toosi H.;Lavagna M.;Leonforte F.;Del Pero C.;Aste N.
2022-01-01

Abstract

Life Cycle Sustainability Assessment (LCSA) in the built environment has increasingly drawn researchers’ attention in the preceding years; however, the lack of an integrated LCSA based model is still a barrier for its effective implementation into the building design process. This paper proposes a new comprehensive LCSA model to be integrated into the design process of new buildings and energy refurbishment scenarios of existing ones. The proposed model consists of sets of mathematic equations to describe LCSA pillars of buildings, including Life Cycle Assessment (LCA), Life Cycle Costing (LCC), and Social Life Cycle Assessment (SLCA) as the intermediate indices. A final LCSA index is then provided to describe a design scenario's performance from an LCSA perspective using the authors' new formulation and weighting method. The model is also integrated into the optimization process and enhanced with Machine Learning (ML) methods to accelerate the design-assessment process while preserving its accuracy. Finally, given the transition towards buildings' electrification by Renewable Energy Sources (RESs), as a supportive technology, the size-optimization of a residential building's short-term thermal and electrical Energy Storage Systems (ESSs) is chosen to demonstrate the model's capabilities. For this purpose, the building case study is parametrically modeled in Grasshopper, Energy plus, and Matlab for energy analysis, data processing, and machine learning.
2022
Building energy retrofitting
Energy storage
Life cycle sustainability assessment
Machine learning
Optimization
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11311/1204565
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 11
social impact