Fast and Reliable $N - k$ Contingency Screening with Input-Convex Neural Networks

Nicolas Christianson, Wenqi Cui, Steven Low, Weiwei Yang, Baosen Zhang
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:527-539, 2025.

Abstract

Power system operators must ensure that dispatch decisions remain feasible in case of grid outages or contingencies to prevent cascading failures and ensure reliable operation. However, checking the feasibility of all $N - k$ contingencies – every possible simultaneous failure of $k$ grid components – is computationally intractable even for small $k$, requiring system operators to resort to heuristic screening methods. Because of the increase in uncertainty and changes in system behaviors, heuristic lists might not include all relevant contingencies, generating false negatives in which unsafe scenarios are misclassified as safe. In this work, we propose to use input-convex neural networks (ICNNs) for contingency screening. We show that ICNN reliability can be determined by solving a convex optimization problem, and by scaling model weights using this problem as a differentiable optimization layer during training, we can learn an ICNN classifier that is both data-driven and has provably guaranteed reliability. That is, our method can ensure a zero false negative rate. We empirically validate this methodology in a case study on the IEEE 39-bus test network, observing that it yields substantial (10-20x) speedups while having excellent classification accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-christianson25a, title = {Fast and Reliable $N - k$ Contingency Screening with Input-Convex Neural Networks}, author = {Christianson, Nicolas and Cui, Wenqi and Low, Steven and Yang, Weiwei and Zhang, Baosen}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {527--539}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/christianson25a/christianson25a.pdf}, url = {https://proceedings.mlr.press/v283/christianson25a.html}, abstract = {Power system operators must ensure that dispatch decisions remain feasible in case of grid outages or contingencies to prevent cascading failures and ensure reliable operation. However, checking the feasibility of all $N - k$ contingencies – every possible simultaneous failure of $k$ grid components – is computationally intractable even for small $k$, requiring system operators to resort to heuristic screening methods. Because of the increase in uncertainty and changes in system behaviors, heuristic lists might not include all relevant contingencies, generating false negatives in which unsafe scenarios are misclassified as safe. In this work, we propose to use input-convex neural networks (ICNNs) for contingency screening. We show that ICNN reliability can be determined by solving a convex optimization problem, and by scaling model weights using this problem as a differentiable optimization layer during training, we can learn an ICNN classifier that is both data-driven and has provably guaranteed reliability. That is, our method can ensure a zero false negative rate. We empirically validate this methodology in a case study on the IEEE 39-bus test network, observing that it yields substantial (10-20x) speedups while having excellent classification accuracy.} }
Endnote
%0 Conference Paper %T Fast and Reliable $N - k$ Contingency Screening with Input-Convex Neural Networks %A Nicolas Christianson %A Wenqi Cui %A Steven Low %A Weiwei Yang %A Baosen Zhang %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-christianson25a %I PMLR %P 527--539 %U https://proceedings.mlr.press/v283/christianson25a.html %V 283 %X Power system operators must ensure that dispatch decisions remain feasible in case of grid outages or contingencies to prevent cascading failures and ensure reliable operation. However, checking the feasibility of all $N - k$ contingencies – every possible simultaneous failure of $k$ grid components – is computationally intractable even for small $k$, requiring system operators to resort to heuristic screening methods. Because of the increase in uncertainty and changes in system behaviors, heuristic lists might not include all relevant contingencies, generating false negatives in which unsafe scenarios are misclassified as safe. In this work, we propose to use input-convex neural networks (ICNNs) for contingency screening. We show that ICNN reliability can be determined by solving a convex optimization problem, and by scaling model weights using this problem as a differentiable optimization layer during training, we can learn an ICNN classifier that is both data-driven and has provably guaranteed reliability. That is, our method can ensure a zero false negative rate. We empirically validate this methodology in a case study on the IEEE 39-bus test network, observing that it yields substantial (10-20x) speedups while having excellent classification accuracy.
APA
Christianson, N., Cui, W., Low, S., Yang, W. & Zhang, B.. (2025). Fast and Reliable $N - k$ Contingency Screening with Input-Convex Neural Networks. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:527-539 Available from https://proceedings.mlr.press/v283/christianson25a.html.

Related Material