English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With growing security and privacy concerns in the Smart Grid domain,intrusion detection on critical energy infrastructure has become a highpriority in recent years. To remedy the challenges of privacy preservation anddecentralized power zones with strategic data owners, Federated Learning (FL)has contemporarily surfaced as a viable privacy-preserving alternative whichenables collaborative training of attack detection models without requiring thesharing of raw data. To address some of the technical challenges associatedwith conventional synchronous FL, this paper proposes FeDiSa, a novelSemi-asynchronous Federated learning framework for power system faults andcyberattack Discrimination which takes into account communication latency andstragglers. Specifically, we propose a collaborative training of deepauto-encoder by Supervisory Control and Data Acquisition sub-systems whichupload their local model updates to a control centre, which then perform asemi-asynchronous model aggregation for a new global model parameters based ona buffer system and a preset cut-off time. Experiments on the proposedframework using publicly available industrial control systems datasets revealsuperior attack detection accuracy whilst preserving data confidentiality andminimizing the adverse effects of communication latency and stragglers.Furthermore, we see a 35% improvement in training time, thus validating therobustness of our proposed method.

FeDiSa: A Semi-asynchronous Federated Learning Framework for Power System Fault and Cyberattack Discrimination