Unbalanced power anomaly detection model based on improved transformer and countermeasure encoder

Shuai Yang, Yanjun Song · 2025

Read Unbalanced power anomaly detection model based on improved transformer and countermeasure encoder by Shuai Yang, Yanjun Song (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12824226.txt.

Description

Yang and Song proposed this model in twenty twenty-five for spotting faults in power grid data. Fault records are rare next to normal ones, so detection tools often miss the cases that matter. Long data streams also strain computer memory. The authors combined a transformer model with a second network that learns to rebuild normal patterns.

Their design groups similar signals to cut memory use by about half. Weighting rules give rare fault cases more say during training. On public grid and home energy datasets, the model scored well and ran fast enough for use at the edge of the network. The authors present it as a practical tool for grid upkeep teams.

Catalog record

CREATORShuai Yang, Yanjun Song
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE35 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12824226

Browse the full library · About the Tower of Babel