GridCL for fine-grained load profiling in smart grids under limited labels
Ling Zhang, Jia Wang, Wenhua Zhang, Ke Li, Daizhou Yao, Bowei Yang, Xingsi Ke, Hong Zhao · 2026
Read GridCL for fine-grained load profiling in smart grids under limited labels by Ling Zhang, Jia Wang, Wenhua Zhang, Ke Li, Daizhou Yao, Bowei Yang, Xingsi Ke, Hong Zhao (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-0354752.txt.
Description
Ling Zhang led a team of eight authors on this 2026 smart grid study of sorting households by their daily electricity use patterns, which utilities need for demand programs. Labeled examples are scarce, so their system, GridCL, learns from unlabeled data by comparing slightly altered versions of each day's usage curve.
Across anonymized data from three cities, the method grouped users well and, with only a tenth of users labeled, classified new ones accurately and steadily. Zhang presents self-teaching on raw meter data as a practical answer to the label shortage.
Catalog record
| CREATOR | Ling Zhang, Jia Wang, Wenhua Zhang, Ke Li, Daizhou Yao, Bowei Yang, Xingsi Ke, Hong Zhao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41032 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |