Achieving climate neutrality requires a fundamental transformation of production systems and energy use, driven by technological innovation. In the building sector, virtual representations of physical assets can accelerate this transition by enabling simulation-based evaluation of energy strategies. When combined with Reinforcement Learning (RL), these models support dynamic testing and real-time optimization of building operations. This study presents a simulation framework for assessing and comparing energy management strategies aimed at reducing energy consumption while maintaining thermal comfort. As a case study, the methodology is applied to an existing industrial facility using the BIMtoBEM modeling approach. The framework integrates detailed simulation models with RL-based control to optimize the performance of the Heating, Ventilation, and Air Conditioning (HVAC) system. Two digital models with increasing Levels of Detail, are developed to evaluate the impact of three structural and one mechanical refurbishment scenario, alongside two RL control strategies. By simulating different combinations of physical retrofits and control approaches, the framework enables users to identify the most impactful interventions and make informed decisions based on specific energy-saving goals. Results show that modifying the mechanics of the HVAC system alone leads to a 12% reduction in natural gas consumption, while combining retrofitting with RL can lead to 32% of savings, emphasizing the impact of both physical and control-based interventions.

A BIMtoBEM Framework for Building Retrofit and HVAC Smart Control Assessment / Loffa, Maria Adelaide; Donato, Angelo J.; Mazzarino, Pietro Rando; Macii, Enrico; Osello, Anna; Del Giudice, Matteo; Patti, Edoardo; Bottaccioli, Lorenzo. - (2025), pp. 1-6. (Intervento presentato al convegno 25th EEEIC International Conference on Environment and Electrical Engineering (EEEIC) tenutosi a Chania, Crete (GR) nel 15-18 July, 2025) [10.1109/eeeic/icpseurope64998.2025.11169011].

A BIMtoBEM Framework for Building Retrofit and HVAC Smart Control Assessment

Loffa, Maria Adelaide;Donato, Angelo J.;Mazzarino, Pietro Rando;Macii, Enrico;Osello, Anna;Del Giudice, Matteo;Patti, Edoardo;Bottaccioli, Lorenzo
2025

Abstract

Achieving climate neutrality requires a fundamental transformation of production systems and energy use, driven by technological innovation. In the building sector, virtual representations of physical assets can accelerate this transition by enabling simulation-based evaluation of energy strategies. When combined with Reinforcement Learning (RL), these models support dynamic testing and real-time optimization of building operations. This study presents a simulation framework for assessing and comparing energy management strategies aimed at reducing energy consumption while maintaining thermal comfort. As a case study, the methodology is applied to an existing industrial facility using the BIMtoBEM modeling approach. The framework integrates detailed simulation models with RL-based control to optimize the performance of the Heating, Ventilation, and Air Conditioning (HVAC) system. Two digital models with increasing Levels of Detail, are developed to evaluate the impact of three structural and one mechanical refurbishment scenario, alongside two RL control strategies. By simulating different combinations of physical retrofits and control approaches, the framework enables users to identify the most impactful interventions and make informed decisions based on specific energy-saving goals. Results show that modifying the mechanics of the HVAC system alone leads to a 12% reduction in natural gas consumption, while combining retrofitting with RL can lead to 32% of savings, emphasizing the impact of both physical and control-based interventions.
2025
979-8-3315-9515-9
File in questo prodotto:
File Dimensione Formato  
EEEIC_2025_Loffa_RL_PCMA.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 1.93 MB
Formato Adobe PDF
1.93 MB Adobe PDF Visualizza/Apri
A_BIMtoBEM_Framework_for_Building_Retrofit_and_HVAC_Smart_Control_Assessment.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.97 MB
Formato Adobe PDF
1.97 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

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/11583/3003554