A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks
Summary
This paper presents a machine learning surrogate model to predict component criticality in interdependent power and communication networks, achieving high correlation with a high-fidelity simulator while being computationally efficient.
View Cached Full Text
Cached at: 07/13/26, 07:56 AM
# A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks Source: [https://arxiv.org/abs/2607.08918](https://arxiv.org/abs/2607.08918) [View PDF](https://arxiv.org/pdf/2607.08918) > Abstract:Cyber\-physical power systems are vulnerable to cascading failures caused by tight interdependencies between power and communication infrastructures\. Evaluating these failures over large N\-k contingency sets with a high\-fidelity simulator is computationally prohibitive for resilience planning\. Using the previously published Modified Implicative Interdependency Model \(MIIM\) as the ground\-truth cascade simulator, this paper develops a machine\-learning surrogate that predicts contingency severity from leakage\-free structural features and derives a component\-criticality ranking for prioritized hardening analysis\. On the IEEE 118\-bus system, the Gradient Boosting surrogate achieves Spearman correlations of 0\.849 for per\-contingency severity prediction and 0\.853 for per\-component criticality ranking, while remaining stable across three independently sampled datasets\. MIIM\-derived component criticality itself reproduces only to a Spearman of approximately 0\.85 under the present sampling pipeline, and the surrogate operates at this empirical ceiling to within sampling variation\. Topological centrality measures on the full interdependent network provide meaningful baselines \(Spearman 0\.60\-0\.69\), and feature ablation shows that the surrogate's advantage is driven primarily by inter\-layer dependency information\. These results support a two\-stage workflow in which the surrogate rapidly ranks candidate components and MIIM is reserved for selective verification\. ## Submission history From: Sohini Roy \[[view email](https://arxiv.org/show-email/8579142c/2607.08918)\] **\[v1\]**Thu, 9 Jul 2026 20:22:14 UTC \(799 KB\)
Similar Articles
Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
This paper presents a scalable heterogeneous graph neural network workflow for data-driven optimal power flow surrogate modeling, using distributed training on supercomputers and demonstrating improvements via fine-tuning pretrained models.
Predicting Channel Closures in the Lightning Network with Machine Learning
This paper explores predicting whether Lightning Network channels will close mutually or via forced closure using machine learning on gossip data. An MLP with temporal features outperforms graph-based models, and the dataset is publicly released.
Neural Controlled Differential Equations for EMT-Level Surrogate Modeling of Grid-Forming Inverters
This paper proposes a Neural Controlled Differential Equation (Neural CDE) framework for learning continuous-time surrogate models of grid-forming inverters for EMT simulation, incorporating dual slow/fast pathways and physics-inspired regularization to capture multi-time-scale dynamics.
AI-Driven Surrogate Models for Predicting Electrode-Scale Discharge Behavior in Lithium-Ion Batteries
Introduces a deep learning surrogate pipeline based on Swin3D Transformer to predict spatiotemporal discharge dynamics in lithium-ion batteries, significantly reducing computational cost while improving accuracy over point cloud baselines.
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification
TRACER is an open-source system that trains lightweight ML surrogates on production traces from LLM classification endpoints, routing requests through a parity gate that activates surrogates only when agreement with the original model exceeds a specified threshold. This approach achieves 83-100% surrogate coverage on intent classification benchmarks while maintaining interpretability into handling boundaries and failure modes.