Search

Building performance simulations (BPS) are used to test different designs and systems with the intention of reducing building costs and energy demand while ensuring a comfortable indoor climate. Unfortunately, software for BPS is computationally intensive. This makes it impractical to run thousands of simulations for sensitivity analysis and optimization. Worse yet, millions of simulations may be necessary for a thorough exploration of the high-dimensional design space formed by the many design parameters. This computational issue may be overcome by the creation of fast metamodels. In this paper, we aim to find suitable metamodeling techniques for diverse outputs from BPS. We consider five indicators of building performance and eight test problems for the comparison six popular metamodeling techniques – linear regression with ordinary least squares (OLS), random forest (RF), support vector regression (SVR), multivariate adaptive regression splines, Gaussian process regression (GPR), and neural network (NN). The methods are compared with respect to accuracy, efficiency, ease-of-use, robustness, and interpretability. To conduct a fair and in-depth comparison, a methodological approach is pursued using exhaustive grid searches for model selection assisted by sensitivity analysis. The comparison shows that GPR produces the most accurate metamodels, followed by NN and MARS. GPR is robust and easy to implement but becomes inefficient for large training sets compared to NN and MARS. A coefficient of determination, R 2 , larger than 0.9 have been obtained for the BPS outputs using between 128 and 1024 training points. In contrast, accurate metamodels with R 2 values larger than 0.99 can be achieved for all eight test problems using only 32–256 training points. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a heat storage and cooling concept that utilizes a phase change material (PCM) and a thermally activated building system (TABS) implemented in a hollow core concrete deck. Numerical calculations of the dynamic heat storage capacity of the hollow core concrete deck element with and without microencapsulated PCM are presented. The new concrete deck with microencapsulated PCM is the standard deck on which an additional layer of the PCM concrete was added and, at the same time, the latent heat storage was introduced to the construction. The challenge of numerically simulating the performance of the new deck with PCM concrete is the thermal properties of such a new material, as the PCM concrete is yet to be well defined. The results presented in the paper include models in which the PCM concrete material properties, such as thermal conductivity, and specific heat capacity were first calculated theoretically and subsequently the models were updated with the experimentally determined thermal properties of the PCM concrete. Then, the heat storage of the decks with theoretically and experimentally determined thermal properties were compared with each other. Finally, the results presented in the article highlight the potential of using TABS and PCM in a prefabricated concrete deck element. [Copyright &y& Elsevier]