Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Building energy efficiency: using machine learning algorithms to accurately predict heating load
The use of machine learning techniques to forecast heating load, a crucial component of building energy efficiency is examined in this work. Numerous building characteristics are found to correlate with heating load. Building height, wall area, surface area, roof area, and so forth are some examples of these. With an R-squared score of 0.921, a root mean square error (RMSE) of 2.87, and a mean absolute error (MAE) of 2.14, the models created for this study show high accuracy. With an astounding accuracy rate of 99.2%, the decision tree model excels among the tested algorithms. The exceptional performance of this model highlights its potential for useful applications in heating load prediction. Promising outcomes are also shown by other algorithms, such as logistic regression at 94.14%, K-nearest neighbors at 95.6%, and neural networks at 96.24%. The results of this study demonstrate how machine learning can be used to predict heating load, offering important information for the creation of energy-saving measures. We can contribute to sustainability efforts by designing more energy-efficient buildings by knowing the relationships between building features and heating load. This study is a major advancement in the use of machine learning for energy management in buildings.
Building energy efficiency: using machine learning algorithms to accurately predict heating load
The use of machine learning techniques to forecast heating load, a crucial component of building energy efficiency is examined in this work. Numerous building characteristics are found to correlate with heating load. Building height, wall area, surface area, roof area, and so forth are some examples of these. With an R-squared score of 0.921, a root mean square error (RMSE) of 2.87, and a mean absolute error (MAE) of 2.14, the models created for this study show high accuracy. With an astounding accuracy rate of 99.2%, the decision tree model excels among the tested algorithms. The exceptional performance of this model highlights its potential for useful applications in heating load prediction. Promising outcomes are also shown by other algorithms, such as logistic regression at 94.14%, K-nearest neighbors at 95.6%, and neural networks at 96.24%. The results of this study demonstrate how machine learning can be used to predict heating load, offering important information for the creation of energy-saving measures. We can contribute to sustainability efforts by designing more energy-efficient buildings by knowing the relationships between building features and heating load. This study is a major advancement in the use of machine learning for energy management in buildings.
Building energy efficiency: using machine learning algorithms to accurately predict heating load
Asian J Civ Eng
Ahmadi, Monireh (Autor:in)
Asian Journal of Civil Engineering ; 25 ; 3129-3139
01.06.2024
11 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Building energy efficiency: using machine learning algorithms to accurately predict heating load
| Springer Verlag | 2024
Predicting building energy consumption in urban neighborhoods using machine learning algorithms
| DOAJ | 2024
Load-sensing systems control speed accurately
British Library Online Contents | 1995