Scalable and Reliable State-Aware Inference of High-Impact N-k Contingencies
This work addresses the problem of efficiently managing power grid reliability for operators, offering a method to identify critical contingencies with controllable risk, though it is incremental as it builds on existing techniques like diffusion models and graph neural networks.
The paper tackles the computational challenge of assessing high-impact N-k contingencies in power systems by proposing a scalable, state-aware inference framework that directly generates critical outage scenarios without exhaustive enumeration. Experiments on IEEE benchmark systems show the approach consistently evaluates higher-severity contingencies than uniform sampling for a given budget, enabling more reliable identification of critical outages with reduced computational effort.
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.