all AI news
Power Grid Behavioral Patterns and Risks of Generalization in Applied Machine Learning. (arXiv:2304.10702v1 [eess.SY])
cs.LG updates on arXiv.org arxiv.org
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, …
applications applied machine learning arxiv data data-driven domain knowledge etc grid insights knowledge literature machine machine learning paper patterns power predictions risk risks topology world