Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Energy consumption prediction of industrial HVAC systems using Bayesian Networks
https://orcid.org/0000-0002-2819-6119
https://orcid.org/0009-0002-3728-8514
https://orcid.org/0000-0003-1564-8830
Highlights Bayesian Networks are proposed to predict HVAC systems energy consumption. Available solutions for each phase of the Bayesian Network building are evaluated. The obtained Bayesian model is compared with other data-based approaches. Results show mostly consistent performance, as well as flexibility and simplicity. The validity of the physical interpretation of the model is demonstrated.
Abstract Predicting energy consumption has become a critical issue for energy-intensive industrial contexts. A significant contribution to their overall energy load is due to the Heating Ventilation and Air Conditioning (HVAC) systems. This work, therefore, aims to validate the applicability of a probabilistic graphical approach, the Bayesian Network, in predicting the HVAC systems' energy consumption. As a data-driven approach, it is compared with more common AI-based models like Support Vector Machine, Artificial Neural Networks and Random Forest. The graphical approach ensures a better interpretation of the main factors determining the energy consumption and the relationships underlying these dependences. After an initial contextualisation and an analysis of the state of the art, the design methodology of a Bayesian network is investigated in detail, deepening in the various solutions for each step and evaluating their performance through the application on two industrial case studies. The results show that Bayesian networks, despite not always providing the best results, are a valid solution, trading off between simplicity, flexibility, and performance. Moreover, the possibility to provide a physical interpretation of the results is one of its main strengths. The critical aspect encountered, instead, is the need for discretisation, which strongly influences the quality of the results.
Energy consumption prediction of industrial HVAC systems using Bayesian Networks
https://orcid.org/0000-0002-2819-6119
https://orcid.org/0009-0002-3728-8514
https://orcid.org/0000-0003-1564-8830
Highlights Bayesian Networks are proposed to predict HVAC systems energy consumption. Available solutions for each phase of the Bayesian Network building are evaluated. The obtained Bayesian model is compared with other data-based approaches. Results show mostly consistent performance, as well as flexibility and simplicity. The validity of the physical interpretation of the model is demonstrated.
Abstract Predicting energy consumption has become a critical issue for energy-intensive industrial contexts. A significant contribution to their overall energy load is due to the Heating Ventilation and Air Conditioning (HVAC) systems. This work, therefore, aims to validate the applicability of a probabilistic graphical approach, the Bayesian Network, in predicting the HVAC systems' energy consumption. As a data-driven approach, it is compared with more common AI-based models like Support Vector Machine, Artificial Neural Networks and Random Forest. The graphical approach ensures a better interpretation of the main factors determining the energy consumption and the relationships underlying these dependences. After an initial contextualisation and an analysis of the state of the art, the design methodology of a Bayesian network is investigated in detail, deepening in the various solutions for each step and evaluating their performance through the application on two industrial case studies. The results show that Bayesian networks, despite not always providing the best results, are a valid solution, trading off between simplicity, flexibility, and performance. Moreover, the possibility to provide a physical interpretation of the results is one of its main strengths. The critical aspect encountered, instead, is the need for discretisation, which strongly influences the quality of the results.
Energy consumption prediction of industrial HVAC systems using Bayesian Networks
https://orcid.org/0000-0002-2819-6119
https://orcid.org/0009-0002-3728-8514
https://orcid.org/0000-0003-1564-8830
Highlights Bayesian Networks are proposed to predict HVAC systems energy consumption. Available solutions for each phase of the Bayesian Network building are evaluated. The obtained Bayesian model is compared with other data-based approaches. Results show mostly consistent performance, as well as flexibility and simplicity. The validity of the physical interpretation of the model is demonstrated.
Abstract Predicting energy consumption has become a critical issue for energy-intensive industrial contexts. A significant contribution to their overall energy load is due to the Heating Ventilation and Air Conditioning (HVAC) systems. This work, therefore, aims to validate the applicability of a probabilistic graphical approach, the Bayesian Network, in predicting the HVAC systems' energy consumption. As a data-driven approach, it is compared with more common AI-based models like Support Vector Machine, Artificial Neural Networks and Random Forest. The graphical approach ensures a better interpretation of the main factors determining the energy consumption and the relationships underlying these dependences. After an initial contextualisation and an analysis of the state of the art, the design methodology of a Bayesian network is investigated in detail, deepening in the various solutions for each step and evaluating their performance through the application on two industrial case studies. The results show that Bayesian networks, despite not always providing the best results, are a valid solution, trading off between simplicity, flexibility, and performance. Moreover, the possibility to provide a physical interpretation of the results is one of its main strengths. The critical aspect encountered, instead, is the need for discretisation, which strongly influences the quality of the results.
Energy consumption prediction of industrial HVAC systems using Bayesian Networks
Ciampi, Francesco Giuseppe (Autor:in) / Rega, Andrea (Autor:in) / Diallo, Thierno M.L. (Autor:in) / Pelella, Francesco (Autor:in) / Choley, Jean-Yves (Autor:in) / Patalano, Stanislao (Autor:in)
Energy and Buildings ; 309
24.02.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Cool VRF Technology: New Systems for Reducing HVAC Energy Consumption
Online Contents | 2011
Impacts of Air Filters on Energy Consumption in Typical HVAC Systems
| British Library Online Contents | 2012
Hvac system energy consumption of various business facilities
| British Library Online Contents | 1997