Automated machine learning-based framework of heating and cooling load prediction for quick residential building design. (1st July 2023)

• Record Type: Journal Article
• Authors: Lu, Chujie; Li, Sihui; Reddy Penaka, Santhan; Olofsson, Thomas
• Is Part Of: Energy. Volume 274(2023)
• Publication Date: 2023-07-01
• Subjects: Heating and cooling load -- Energy-efficient building -- Residential building design -- Automated machine learning; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2023.127334
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Reducing the heating and cooling load through energy-efficient building design can help decarbonize the building sector. Heating and cooling load prediction using machine learning (ML) techniques become increasingly important in the rapid assessment of building design variables at the early design stage. However, when applying the ML techniques, it still requires expert knowledge and manually frequent intervention to improve the prediction performance. Hence, this study proposed an automated machine learning (AutoML)-based framework to automatically generate the optimal ML pipelines for heating and cooling load prediction. An experimental dataset of residential buildings was used to evaluate the proposed framework. The proposed framework achieved the best performance with R 2 of 0.9965 and RMSE of 0.602 kWh/m 2 for heating load prediction, and R 2 of 0.9899 and RMSE of 0.973 kWh/m 2 for cooling load prediction. The prediction results showed that the proposed framework outperformed the other improved ML models from the representative studies in the last five years. Further, an explainable analysis of the ML models was explored to reveal the relationships between design variables and heating and cooling load. The proposed framework aims at promoting the AutoML-based framework to designers for building energy performance prediction without excessive ML knowledge and manually frequent intervention. Highlights: An AutoML-based framework is proposed for building energy prediction. A widely used dataset with eight common building design variables is applied. The proposed framework outperforms other improved models from the last five years. The explainable analysis is presented to comprehend predictions of the ML models. Tree-based models have better performance in the building energy prediction.