Very short-term production prediction for photovoltaic plants using Temporal Convolutional Networks
Loukas Samaras, Elena García-Barriocanal, Miguel-Angel Sicilia, Lino González García · 2026
Read Very short-term production prediction for photovoltaic plants using Temporal Convolutional Networks by Loukas Samaras, Elena García-Barriocanal, Miguel-Angel Sicilia, Lino González García (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-0354512.txt.
Description
Loukas Samaras and three colleagues published this 2026 energy study on forecasting Spain's solar power output minutes to an hour ahead. Grid operators need such nowcasts to balance supply. Using national generation records plus past weather readings, they trained a temporal convolutional network, a deep learning design built for sequences, and compared it with plain regression.
The network won clearly at the one-hour horizon and consistently at fifteen minutes. Notably, past weather alone sufficed; no future weather forecast was needed as input. Samaras offers the approach for folding more solar power into national grids.
Catalog record
| CREATOR | Loukas Samaras, Elena García-Barriocanal, Miguel-Angel Sicilia, Lino González García |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69174 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |