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

arXiv: https://arxiv.org/abs/2304.10702 · HTML: https://mlsanity.com/paper/2304.10702/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 21 Apr 2023.

## Builds on (most cited first, 10 of 10)

- [DC3: A learning method for optimization with hard constraints](https://mlsanity.com/paper/2104.12225/) (2021)
- [End-to-End Constrained Optimization Learning: A Survey](https://mlsanity.com/paper/2103.16378/) (2021)
- [Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow](https://mlsanity.com/paper/1910.01213/) (2019)
- [Physics-Guided Deep Neural Networks for Power Flow Analysis](https://mlsanity.com/paper/2002.00097/) (2020)
- [Dynamic Graph-Based Anomaly Detection in the Electrical Grid](https://mlsanity.com/paper/2012.15006/) (2020)
- [Gradient-Enhanced Physics-Informed Neural Networks for Power Systems Operational Support](https://mlsanity.com/paper/2206.10579/) (2022)
- [Koopman-based Differentiable Predictive Control for the Dynamics-Aware Economic Dispatch Problem](https://mlsanity.com/paper/2203.08984/) (2022)
- [Contingency Analyses with Warm Starter using Probabilistic Graphical Model](https://mlsanity.com/paper/2304.06727/) (2023)
- [On the Feasibility of Load-Changing Attacks in Power Systems during the COVID-19 Pandemic](https://mlsanity.com/paper/2011.09982/) (2020)
- [Towards Practical Physics-Informed ML Design and Evaluation for Power Grid](https://mlsanity.com/paper/2205.03673/) (2022)

## Built on by (most cited first, 1 of 1)

- [PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis](https://mlsanity.com/paper/2509.12212/) (2025)

## Abstract (arXiv)

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.