What type of study is this?

This is a Quantitative Study study.

October 11, 2025ACM Transactions on Cyber-Physical SystemsOpen Access

Achieving Robustness and Dropout Fairness with Hierarchical Federated Learning in Smart Grid Infrastructures

View Full Paper

Ask AI

Bookmark

Authors

CLCody LewisUniversity of Newcastle Australia VVVijay VaradharajanUniversity of Newcastle Australia NNNasimul NomanUniversity of Newcastle Australia

Discussion

Member takes

Implication

Proposed framework enhances data privacy and client dropout resilience in smart grid systems, indicating effective integration of federated learning techniques.

Key Points

The proposed SGHFL framework significantly improves dropout resilience and robustness against data poisoning.
Evaluation across three datasets demonstrates the effectiveness of the SGHFL framework in real-world smart grid applications.
The framework leverages lightweight models, catering to the limitations of devices in smart grid environments.
Theoretical justification supports the design and implementation of the SGHFL framework in existing smart grid architectures.

Cite This Study

Lewis et al. (2025) studied this question.

synapsesocial.com/papers/68e9b1b5ba7d64b6fc131fbb https://doi.org/10.1145/3771547

View Full Paper

Ask AI

Bookmark

Implication

Proposed framework enhances data privacy and client dropout resilience in smart grid systems, indicating effective integration of federated learning techniques.

Achieving Robustness and Dropout Fairness with Hierarchical Federated Learning in Smart Grid Infrastructures

Discussion

Member takes

Implication

Key Points

Cite This Study

Achieving Robustness and Dropout Fairness with Hierarchical Federated Learning in Smart Grid Infrastructures

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider