Short-term photovoltaic power forecasting using DTW-based K-Medoids clustering and a hybrid VMD-CEEMDAN-1DCNN-S-Mamba model
Hu Tianxiang, Gao Li, ChenLi Tianxi, Xie Congjiu, Xu Mingshen, Wu Peng · 2026
Read Short-term photovoltaic power forecasting using DTW-based K-Medoids clustering and a hybrid VMD-CEEMDAN-1DCNN-S-Mamba model by Hu Tianxiang, Gao Li, ChenLi Tianxi, Xie Congjiu, Xu Mingshen, Wu Peng (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/PMC13550647.txt.
Description
Hu Tianxiang, with five colleagues, published a 2026 method for forecasting solar power output a short time ahead. Clouds make photovoltaic generation swing sharply, which threatens grid stability. The approach first groups past days into sunny, cloudy, and rainy patterns using a time-warping cluster method, then splits the power signal into trend and residual parts with two decomposition techniques.
A hybrid network reads the cleaned components along with weather variables, using convolutional layers for local patterns and a bidirectional state-space model for longer links. On two years of five-minute data from three Australian stations, forecasts were highly accurate and beat eleven rival models, especially in cloudy and rainy weather. Removing parts of the design weakened results, supporting each piece.
Catalog record
| CREATOR | Hu Tianxiang, Gao Li, ChenLi Tianxi, Xie Congjiu, Xu Mingshen, Wu Peng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79251 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |