Scalable and Reliable State-Aware Inference of High-Impact N-k Contingencies

2026-02-10

AI Summary

This work addresses the challenge of efficiently assessing high-order N-k contingency risk under high inverter penetration and rapidly varying operating conditions, where traditional methods fall short. The authors propose a scalable, state-aware contingency inference framework that uniquely integrates conditional diffusion models with topology-aware graph neural networks to directly generate high-impact N-k fault scenarios aligned with the current system state—without exhaustive enumeration. By combining AC power flow simulations with an offline training strategy based on N-1 data, the method significantly outperforms uniform sampling on IEEE benchmark systems: under identical computational budgets, it identifies more severe contingencies, substantially improving both the reliability and efficiency of critical fault detection while providing provable guarantees on coverage of severe events.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Increasing penetration of inverter-based resources, flexible loads, and rapidly changing operating conditions make higher-order $N\!-\!k$ contingency assessment increasingly important but computationally prohibitive. Exhaustive evaluation of all outage combinations using AC power-flow or ACOPF is infeasible in routine operation. This fact forces operators to rely on heuristic screening methods whose ability to consistently retain all critical contingencies is not formally established. This paper proposes a scalable, state-aware contingency inference framework designed to directly generate high-impact $N\!-\!k$ outage scenarios without enumerating the combinatorial contingency space. The framework employs a conditional diffusion model to produce candidate contingencies tailored to the current operating state, while a topology-aware graph neural network trained only on base and $N\!-\!1$ cases efficiently constructs high-risk training samples offline. Finally, the framework is developed to provide controllable coverage guarantees for severe contingencies, allowing operators to explicitly manage the risk of missing critical events under limited AC power-flow evaluation budgets. Experiments on IEEE benchmark systems show that, for a given evaluation budget, the proposed approach consistently evaluates higher-severity contingencies than uniform sampling. This allows critical outages to be identified more reliably with reduced computational effort.

Problem

• N-k contingency
• power system security
• computational scalability
• high-impact outages
• state-aware inference

Innovation

• conditional diffusion model
• graph neural network
• state-aware contingency inference
• N-k contingency screening
• coverage guarantee