Cyber-resilient machine learning framework for accurate individual load forecasting and anomaly detection in smart grids

M Tayseer, M Talaat, Amr A Zamel, Bishoy E Sedhom, M Elgamal, Tomonobu Senjyu, Dongran Song, Islam M Ibrahim, M H Elkholy · 2025

Read Cyber-resilient machine learning framework for accurate individual load forecasting and anomaly detection in smart grids by M Tayseer, M Talaat, Amr A Zamel, Bishoy E Sedhom, M Elgamal, Tomonobu Senjyu, Dongran Song, Islam M Ibrahim, M H Elkholy (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-12714707.txt.

Description

Tayseer and co-authors build a guard for smart power grids in a 2025 paper that joins forecasting with attack detection. Grid operators need sharp guesses of each home's power use to run the network well. Fake data attacks on meters can wreck those guesses.

Their system first groups meters with a clustering step, then trains small neural networks per group. That cut forecast error and shrank compute time from days to minutes across four model types. A second model watches the data stream for signs of fake values. Tests used five months of real meter data from Egypt's Suez Canal region. The detector scored high on accuracy in staged attacks, as the authors report.

Catalog record

CREATORM Tayseer, M Talaat, Amr A Zamel, Bishoy E Sedhom, M Elgamal, Tomonobu Senjyu, Dongran Song, Islam M Ibrahim, M H Elkholy
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE84 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12714707

Browse the full library · About the Tower of Babel