Embedding the weather prediction errors (WPE) into the photovoltaic (PV) forecasting method using deep learning
Problem
Photovoltaic power forecasts for on-grid, hybrid and off-grid systems are degraded by weather prediction errors, hurting renewable energy use and market bids.
Why it matters
Accurate PV forecasting is essential for maximizing renewable energy usage and creating performant electricity market bids.
What the AI did
A Stacking Regressor ensemble combined with Weather Prediction Error-based features was used to adjust PV forecasts across four types of PV systems in Energy Communities.
Results
R² increased by more than 3% with the Stacking Regressor versus individual ML models (abstract truncated mid-sentence).
Impact
The evidence supports a measurable but modest forecasting improvement over individual ML models.
Record
| Venue | Journal of Forecasting |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Adela Bârã, Simona‐Vasilica Oprea |
| Citations | 18 (OpenAlex, at import time) |
| References | 50 |
| Model or method | Stacking Regressor (ensemble of ML models) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1002/for.3064 |
| Open access | bronze |
| Keywords | photovoltaic forecasting, stacking regressor, weather prediction error, renewable energy, energy communities |
Importance rating
real but narrower advance
Abstract claims PV forecasting is tremendously important for maximizing renewable energy use and electricity market bids; demonstrated gains are modest (R2 +3-6%, MAE -10-23%) across four PV system types.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|