Computational fluid dynamics (CFD) models have been widely used for prototyping data centers. Evolving them into high-fidelity and real-time digital twins is desirable for online operations of data centers. However, CFD models often have unsatisfactory accuracy and high computation overhead. Manually calibrating the CFD model parameters is tedious and labor-intensive. Existing automatic calibration approaches apply heuristics to search the model configurations. However, each search step requires a long-lasting process of repeatedly solving the CFD model, rendering them impractical especially for complex CFD models. This paper presents Kalibre, a knowledge-based neural surrogate approach that calibrates a CFD model by iterating four steps of i) training a neural surrogate model, ii) finding the optimal parameters through neural surrogate retraining, iii) configuring the found parameters back to the CFD model, and iv) validating the CFD model using sensor-measured data. Thus, the parameter search is offloaded to the lightweight neural surrogate. To speed up Kalibre’s convergence, we incorporate prior knowledge in training data initialization and surrogate architecture design. With about ten hours computation on a 64-core processor, Kalibre achieves mean absolute errors (MAEs) of 0.57°C and 0.88°C in calibrating the CFD models of two production data halls hosting thousands of servers. To accelerate CFD-based simulation, we further propose Kalibreduce that incorporates the energy balance principle to reduce the order of the calibrated CFD model. Evaluation shows the model reduction only introduces 0.1°C to 0.27°C extra errors, while accelerating the CFD-based simulations by thousand times.

计算流体动力学 (CFD) 模型已广泛用于数据中心原型设计。将它们演变成高保真和实时的数字双胞胎对于数据中心的在线运营是可取的。然而，CFD 模型往往精度不高，计算开销大。手动校准 CFD 模型参数既繁琐又费力。现有的自动校准方法应用启发式方法来搜索模型配置。然而，每个搜索步骤都需要一个长期的反复求解 CFD 模型的过程，这使得它们不切实际，尤其是对于复杂的 CFD 模型。本文介绍了Kalibre，一种基于知识的神经替代方法，通过迭代以下四个步骤来校准 CFD 模型：i）训练神经替代模型，ii）通过神经替代再训练找到最佳参数，iii）将找到的参数配置回 CFD 模型，以及iv) 使用传感器测量数据验证 CFD 模型。因此，参数搜索被卸载到轻量级神经代理。为了加速 Kalibre 的收敛，我们在训练数据初始化和代理架构设计中结合了先验知识。通过在 64 核处理器上进行大约 10 小时的计算，Kalibre 在校准托管数千台服务器的两个生产数据大厅的 CFD 模型时实现了 0.57°C 和 0.88°C 的平均绝对误差 (MAE)。为了加速基于 CFD 的仿真，我们进一步提出了Kalibreduce它结合了能量平衡原理来降低校准 CFD 模型的阶数。评估表明，模型缩减仅引入 0.1°C 至 0.27°C 的额外误差，同时将基于 CFD 的模拟加速了数千倍。