Metraipolis › archive › dc_e4b37cd2c297
Reducing Multi-Horizon Photovoltaic Forecast Error through Tree-Anchored Expert Combination — arXiv:2610.31248
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31248
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T20:53:21.620Z
- SHA-256 of the archived text
aa882f9e244c55a4227a4f0ba3a243198c1dff205a7cf9299794474958281b33- Stable URL of this page
https://metraipolis.com/documento/dc_e4b37cd2c297
How to cite
Reducing Multi-Horizon Photovoltaic Forecast Error through Tree-Anchored Expert Combination — arXiv:2610.31248 — arXiv (en), https://arxiv.org/abs/2610.31248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4b37cd2c297 (Metraipolis archive dc_e4b37cd2c297, sha256 aa882f9e244c55a4227a4f0ba3a243198c1dff205a7cf9299794474958281b33)
BibTeX
@misc{dce4b37cd2c297,
title = {Reducing Multi-Horizon Photovoltaic Forecast Error through Tree-Anchored Expert Combination — arXiv:2610.31248},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31248},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4b37cd2c297; sha256 aa882f9e244c55a4227a4f0ba3a243198c1dff205a7cf9299794474958281b33},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A strong direct tree model may remain the best standalone photovoltaic forecaster, yet a weighted combination can reduce its residual errors. We examine whether complementary temporal predictors can lower the tree's mean absolute error (MAE) over 15--240 minutes without weaker ensemble members degrading performance. The candidate bank contains LightGBM and seven neural implementations with different temporal representations. A combiner fitted to MAE has nonnegative weights that sum to one. Unhelpful candidates can receive zero weight, while the tree anchors the combination and provides a development-stage fallback. The main design shares weights across horizons; horizon-specific weights and alternative losses test whether further complexity is needed. On 56,078 windows from two co-located public PVDAQ systems, the historical shared-MAE policy reduces scaled MAE by 3.21\% relative to the tree. The latest bounded neural correction does not reduce MAE further than this static combination. The results support selective combination of complementary predictions in this bank rather than equal averaging or indiscriminate addition of modules. Both analyses reuse a previously inspected evaluation period. They do not establish independent replication, weather-specific causation or universal gains from eight experts. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.31248 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T20:47:56.920Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).