arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.16274cs.LGcs.CEphysics.ao-ph
收藏

利用多保真度深度迁移学习尾流模型加速风电场偏航和布局优化

Accelerated wind farm yaw and layout optimisation with multi-fidelity deep transfer learning wake models

Imperial College London(帝国理工学院);EPFL(洛桑联邦理工学院);ECMWF(欧洲中期天气预报中心)

Sokratis Anagnostopoulos, Jens Bauer, Mariana C. A. Clare, Matthew D. Piggott

摘要:

风电场建模已成为一个迅速增长的兴趣领域,开发了许多基于分析和计算的方法,以扩大风电场效率的边际并最大限度地提高发电量。在这项工作中,我们提出了新的ML框架WakeNet,它可以在很宽的偏航角,风速和湍流强度(TI)范围内再现轮毂高度处的广义2D涡轮机尾流速度场,与使用最先进的风电场建模软件FLORIS计算的解决方案相比,平均精度为99.8%。由于为网络训练目的生成足够的高保真数据可能是成本高昂的,因此还研究了多保真度迁移学习的效用。具体而言,对在低保真度高斯尾流模型上预训练的网络进行微调,以便获得中保真度卷曲尾流模型的准确尾流结果。WakeNet在各种尾流转向控制和布局优化场景中的鲁棒性和整体性能已经通过功率增益热图进行了验证,通过直接使用FLORIS进行优化获得了至少90%的功率。我们还证明,当利用卷曲模型时,WakeNet能够提供与FLORIS相似的功率增益,快两个数量级(例如,每个优化案例10分钟vs 36小时)。在高保真CFD数据集上训练时,wakeNet的尾流评估时间预计相似,从而进一步增加计算时间增益。这些有希望的结果表明,广义尾流建模与ML工具可以是足够准确的,有助于主动偏航和布局优化,同时产生现实的优化配置的一小部分的计算成本,从而使其可行的执行实时主动偏航控制以及鲁棒优化下的不确定性。

英文摘要:

Wind farm modelling has been an area of rapidly increasing interest with numerous analytical as well as computational-based approaches developed to extend the margins of wind farm efficiency and maximise power production. In this work, we present the novel ML framework WakeNet, which can reproduce generalised 2D turbine wake velocity fields at hub-height over a wide range of yaw angles, wind speeds and turbulence intensities (TIs), with a mean accuracy of 99.8% compared to the solution calculated using the state-of-the-art wind farm modelling software FLORIS. As the generation of sufficient high-fidelity data for network training purposes can be cost-prohibitive, the utility of multi-fidelity transfer learning has also been investigated. Specifically, a network pre-trained on the low-fidelity Gaussian wake model is fine-tuned in order to obtain accurate wake results for the mid-fidelity Curl wake model. The robustness and overall performance of WakeNet on various wake steering control and layout optimisation scenarios has been validated through power-gain heatmaps, obtaining at least 90% of the power gained through optimisation performed with FLORIS directly. We also demonstrate that when utilising the Curl model, WakeNet is able to provide similar power gains to FLORIS, two orders of magnitude faster (e.g. 10 minutes vs 36 hours per optimisation case). The wake evaluation time of wakeNet when trained on a high-fidelity CFD dataset is expected to be similar, thus further increasing computational time gains. These promising results show that generalised wake modelling with ML tools can be accurate enough to contribute towards active yaw and layout optimisation, while producing realistic optimised configurations at a fraction of the computational cost, hence making it feasible to perform real-time active yaw control as well as robust optimisation under uncertainty.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑