MambaFormer-TPEF: a hybrid state space-transformer framework with two-stage peak enhancement for ultra-long sequence photovoltaic power forecasting
Jiayu Zou, Xixiu Wu, Qingyong Zhang, Zirui Shao · 2026
Read MambaFormer-TPEF: a hybrid state space-transformer framework with two-stage peak enhancement for ultra-long sequence photovoltaic power forecasting by Jiayu Zou, Xixiu Wu, Qingyong Zhang, Zirui Shao (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/pmc-13408109.txt.
Description
Jiayu Zou and co-authors build in 2026 a forecast frame for sun farm output on long spans. Grid crews need such long calls to hold the grid firm and plan stored power. Long runs fight a clash of speed and grade, and stock loss math tends to call peaks too low.
One half scans long past runs at flat cost while a focus step reads fine swings. A twin peak boost then splits peak size from peak time calls. A stack blend weighs the parts per scene. On real data for a week ahead span, the frame set a top mark and cut peak skew.
Catalog record
| CREATOR | Jiayu Zou, Xixiu Wu, Qingyong Zhang, Zirui Shao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |