Recent years have seen a rich literature of data-driven approaches designed for power grid applications. However, insufficient consideration of domain knowledge can impose a high risk to the practicality of the methods. Specifically, ignoring the grid-specific spatiotemporal patterns (in load, generation, and topology, etc.) can lead to outputting infeasible, unrealizable, or completely meaningless predictions on new inputs. To address this concern, this paper investigates real-world operational data to provide insights into power grid behavioral patterns, including the time-varying topology, load, and generation, as well as the spatial differences (in peak hours, diverse styles) between individual loads and generations. Then based on these observations, we evaluate the generalization risks in some existing ML works causedby ignoring these grid-specific patterns in model design and training.

翻译：近年来，针对电网应用的数据驱动方法研究文献日益丰富。然而，对领域知识考虑不足可能给方法的实用性带来高风险。具体而言，忽视电网特有的时空模式（如负荷、发电及拓扑结构等）可能导致在新输入上输出不可行、不可实现或完全无意义的预测。为应对这一挑战，本文通过对真实运行数据的分析，深入探究电网行为模式，包括时变拓扑、负荷与发电特性，以及各负荷和发电单元之间的空间差异（如高峰时段、多样化风格）。基于这些观察，我们评估了现有机器学习研究因在模型设计与训练中忽视这些电网特有模式而导致的泛化风险。