Data-driven wind turbine wake modeling via probabilistic machine learning
Data-driven wind turbine wake modeling via probabilistic machine learning
复制标题
DOI：
10.1007/s00521-021-06799-6
复制
发表时间：
2022-01
影响因子：
6
通讯作者：
S. Ashwin Renganathan;R. Maulik;S. Letizia;G. Iungo
中科院分区：
文献类型：
--
作者：
S. Ashwin Renganathan;R. Maulik;S. Letizia;G. Iungo
风电场设计主要取决于风力涡轮机尾流对大气风况的变化性以及尾流之间的相互作用。以高保真度捕获尾流场的基于物理的模型对于执行风电场布局优化来说计算成本非常高，因此，数据驱动的降阶模型可以代表模拟风电场的有效替代方案。在这项工作中，我们使用真实世界的光探测和测距（LiDAR）测量风力涡轮机尾流，使用机器学习来构建预测代理模型。具体来说，我们首先演示了使用深度自动编码器来找到一个低维的latentspace，它给出了尾流激光雷达测量的计算上易于处理的近似。然后，我们使用深度神经网络学习参数空间和（潜在空间）尾流场之间的映射。此外，我们还展示了使用概率机器学习技术，即高斯过程建模，学习参数空间潜在空间映射除了数据中的认识和任意的不确定性。最后，为了科普训练大型数据集，我们演示了变分高斯过程模型的使用，该模型为大型数据集的传统高斯过程模型提供了一种易于处理的替代方案。此外，我们介绍了使用主动学习自适应地建立和提高传统的高斯过程模型的预测能力。总的来说，我们发现，我们的方法提供了准确的近似风力涡轮机尾流场，可以查询的数量级便宜的成本比那些产生的高保真基于物理的模拟。
Wind farm design primarily depends on the variability of the wind turbine wake flows to the atmospheric wind conditions and the interaction between wakes. Physics-based models that capture the wake flow field with high-fidelity are computationally very expensive to perform layout optimization of wind farms, and, thus, data-driven reduced-order models can represent an efficient alternative for simulating wind farms. In this work, we use real-world light detection and ranging (LiDAR) measurements of wind-turbine wakes to construct predictive surrogate models using machine learning. Specifically, we first demonstrate the use of deep autoencoders to find a low-dimensionallatentspace that gives a computationally tractable approximation of the wake LiDAR measurements. Then, we learn the mapping between the parameter space and the (latent space) wake flow fields using a deep neural network. Additionally, we also demonstrate the use of a probabilistic machine learning technique, namely, Gaussian process modeling, to learn the parameter-space-latent-space mapping in addition to the epistemic and aleatoric uncertainty in the data. Finally, to cope with training large datasets, we demonstrate the use of variational Gaussian process models that provide a tractable alternative to the conventional Gaussian process models for large datasets. Furthermore, we introduce the use of active learning to adaptively build and improve a conventional Gaussian process model predictive capability. Overall, we find that our approach provides accurate approximations of the wind-turbine wake flow field that can be queried at an orders-of-magnitude cheaper cost than those generated with high-fidelity physics-based simulations.