Machine learning model predicts cascading failures in power-communication networks

Researchers have developed a machine learning surrogate model to predict cascading failures in interdependent power and communication networks. This model uses gradient boosting to achieve high correlation with a high-fidelity simulator, enabling rapid ranking of critical components for infrastructure hardening. The surrogate model's effectiveness is driven by its ability to incorporate inter-layer dependency information, outperforming traditional topological centrality measures. AI

IMPACT Enables faster and more efficient resilience planning for critical infrastructure by predicting cascading failures.

RANK_REASON Academic paper detailing a new machine learning model for network analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• gradient boosting
• IEEE 118-bus system
• Modified Implicative Interdependency Model
• Spearman

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →