A measurement-driven graph learning framework for Wideband oscillation localization in power systems

Zhilin Dong, Haoqing Xiong, Jun Yang, Rongqiang Su, Qianfeng Shen, Shaohua Zhang, Yixin Chang, Jiaxu Chen · 2026

Read A measurement-driven graph learning framework for Wideband oscillation localization in power systems by Zhilin Dong, Haoqing Xiong, Jun Yang, Rongqiang Su, Qianfeng Shen, Shaohua Zhang, Yixin Chang, Jiaxu Chen (2026) 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/plos-pone-0355190.txt.

Description

Zhilin Dong and co-authors propose in 2026 a graph learning method to locate the source of wide range oscillations in modern power grids rich in electronic converters. Such wobbles span many frequencies, shift quickly, and fade fast with distance, defeating methods built for slow, narrow wobbles. Their network splits signals into a smooth global branch and a local contrast branch, then fuses them adaptively.

Benchmark grid simulations showed the method beat several time based and graph based rivals, with the clearest gain at high frequencies where smoothing methods erase the source signal. A larger benchmark gave early support for scale. Real large grid testing is still needed, the authors note.

Catalog record

CREATORZhilin Dong, Haoqing Xiong, Jun Yang, Rongqiang Su, Qianfeng Shen, Shaohua Zhang, Yixin Chang, Jiaxu Chen
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE78863
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355190

Browse the full library · About the Tower of Babel