DeepAI AI Chat
Log In Sign Up

Power Grid Behavioral Patterns and Risks of Generalization in Applied Machine Learning

by   Shimiao Li, et al.
Carnegie Mellon University

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.


page 1

page 2

page 3

page 4


Optimal Load Scheduling Using Genetic Algorithm to Improve the Load Profile

Stability and protection of the electrical power systems are always of p...

GridWarm: Towards Practical Physics-Informed ML Design and Evaluation for Power Grid

When applied to a real-world safety critical system like the power grid,...

Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring

Residential buildings with the ability to monitor and control their net-...

Extreme Scenario Selection in Day-Ahead Power Grid Operational Planning

We propose and analyze the application of statistical functional depth m...

Topology-aware Robust Optimization for Out-of-distribution Generalization

Out-of-distribution (OOD) generalization is a challenging machine learni...

Contingency Analyses with Warm Starter using Probabilistic Graphical Model

Cyberthreats are an increasingly common risk to the power grid and can t...