A comparison of six metamodeling techniques applied to building performance simulations
A comparison of six metamodeling techniques applied to building performance simulations
复制标题
DOI：
10.1016/j.apenergy.2017.10.102
复制
发表时间：
2018-02-01
期刊：
影响因子：
11.2
通讯作者：
Maagaard, Steffen Enersen
中科院分区：
文献类型：
--
作者：
Ostergard, Torben;Jensen, Rasmus Lund;Maagaard, Steffen Enersen
建筑性能模拟（BPS）用于测试不同的设计和系统，旨在降低建筑成本和能源需求，同时确保舒适的室内气候。不幸的是，用于BPS的软件是计算密集型的。这使得运行数千次模拟进行灵敏度分析和优化变得不切实际。更糟糕的是，为了彻底探索由许多设计参数形成的高维设计空间，可能需要数百万次的模拟。这个计算问题可以通过创建快速元模型来克服。在本文中，我们的目标是找到合适的元建模技术，从BPS的不同输出。我们考虑了建筑性能的五个指标和八个测试问题，以比较六种流行的元建模技术--普通最小二乘线性回归（OLS）、随机森林（RF）、支持向量回归（SVR）、多元自适应回归样条、高斯过程回归（GPR）和神经网络（NN）。这些方法进行了比较的准确性，效率，易用性，鲁棒性和可解释性。为了进行公平和深入的比较，采用了一种方法学的方法，使用详尽的网格搜索进行模型选择，并辅之以敏感性分析。比较表明，GPR产生最准确的元模型，其次是NN和MARS。GPR是强大的，易于实现，但变得低效的大型训练集相比，神经网络和MARS。使用128至1024个训练点，BPS输出的决定系数R-2大于0.9。相比之下，仅使用32-256个训练点就可以为所有8个测试问题实现R-2值大于0.99的准确元模型。
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.