Predicting day-ahead solar irradiance through gated recurrent unit using weather forecasting data
Problem
Solar power operators need accurate day-ahead irradiance forecasts for planning, scheduling and managing photovoltaic plants and grid-connected systems.
Why it matters
Irradiance forecast errors raise costs and grid-management risks for solar power operators.
What the AI did
A novel gated recurrent unit (GRU) network combined with weather forecast data predicts solar irradiance over a 24-hour horizon.
Results
RMSE reduced 23.3% vs backpropagation neural network and 11.9% vs RNN; training time reduced 36.6% vs LSTM.
Impact
Peer-reviewed method with quantified gains over prior AI forecasting approaches.
Record
| Venue | Journal of Renewable and Sustainable Energy |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Bixuan Gao, Xiaoqiao Huang, Junsheng Shi, Yonghang Tai, Rui Xiao |
| Citations | 51 (OpenAlex, at import time) |
| References | 51 |
| Model or method | Gated recurrent unit (GRU) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1063/1.5110223 |
| Open access | closed |
| Keywords | solar irradiance, forecasting, GRU, neural networks, renewable energy |
Importance rating
significant — thousands to millions affected
Abstract states irradiance forecasts are needed for planning, scheduling, and managing photovoltaic plants and grid-combined systems across the solar power industry; forecast quality affects operations.
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
|