What question did this study set out to answer?

The research aims to develop a privacy-preserving AI system for predicting outage risks in power grids using federated learning.

April 26, 2026Open Access

Privacy-Preserving Federated Learning for Feeder-Level Outage Prediction in Distribution Grids

Key Points

The research aims to develop a privacy-preserving AI system for predicting outage risks in power grids using federated learning.
Developed an AI system utilizing federated learning for cross-utility data management.
Implemented differential privacy and secure aggregation for data confidentiality.
Conducted experiments comparing federated and isolated local models to evaluate performance.
Federated models outperformed isolated local models significantly.
Maintained strong performance under privacy constraints (ε ≈ 1.0).
Identified challenges in applying graph-based models across diverse grid topologies.

Abstract

This project develops an AI system to predict feeder-level outage risk across power grids without sharing raw utility data. It leverages federated learning to enable cross-utility collaboration, combined with differential privacy and secure aggregation to ensure data confidentiality. Experiments show that federated models significantly outperform isolated local models while maintaining strong performance under strict privacy constraints (ε ≈ 1.0). The work also highlights key challenges in applying graph-based models across heterogeneous grid topologies, revealing important directions for future research in scalable, privacy-safe grid intelligence.

Privacy-Preserving Federated Learning for Feeder-Level Outage Prediction in Distribution Grids

Key Points

Abstract

Cite This Study