Fuzzy granulation improves wind-speed forecasts in three Penglai site datasets
Source check: Source checked. Not independent scientific confirmation.
Finding: A fuzzy-information-granulation ensemble combines neural predictors for wind-speed forecasting. On three 10-minute-resolution Penglai wind-farm datasets (7,110 observations per site, split 5:2 for training and testing), reported one-step MAPE was 7.86%, 5.18%, and 14.56% for the three datasets. These are held-out results from the study data, not prospective wind-farm operating outcomes.
Technology: Fuzzy-information-granulation ensemble with multiple neural predictors and multi-objective tuna-swarm optimization
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Fuzzy-information-granulation preprocessing and a multi-objective optimizer combine forecasts from multiple neural predictors.
- Test and result
- Three 10-minute-resolution datasets from different Penglai wind-farm sites, each with 7,110 observations and a 5:2 train/test split. The designed system reported one-step MAPE of 7.86%, 5.18%, and 14.56% across the three datasets.
- Limitation / still unknown
- The evaluation uses held-out data from one wind farm; prospective operating outcomes and validation at other wind farms are not established in the reviewed material.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12750007/ · https://pubmed.ncbi.nlm.nih.gov/41461667/ · https://europepmc.org/article/MED/41461667
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.