Solar Forecasting Based on All Sky Imaging, Long Short Term Memory
A Dutch research team have developed a solar radiation forecasting model that uses the long short-term memory (LSTM) technique. The proposed methodology reportedly achieves better results than other forecasting approaches.
PV Magazine International 4:52 pm on April 23, 2024
A Dutch research team developed a solar radiation forecasting model using long short-term memory (LSTM) technique. The LSTM model, a type of recurrent neural network, takes relevant parts of pre-trained machine learning models and applies them to new problems, enabling it to form future representations of the sky's evolution. The team utilized all-sky cameras and sensors at the Plataforma Solar de Almera facility in Spain for training their model, which outperformed other machine learning methods such as Random Forest (RF) and Artificial Neural Networks (ANN), demonstrating superior temporal dynamics crucial for solar forecasting.
- Researchers from the Netherlands Utrecht University and EKO Instruments Europe developed a novel machine learning and all-sky imaging-based short-term solar irradiance forecasting model.
- The model uses long short-term memory (LSTM) technique, which is a type of recurrent neural network capable of learning order dependence in sequence prediction problems.
- The team utilized all-sky cameras and sensors at the Plataforma Solar de Almera facility to collect data for training their model.
- The LSTM model outperformed other machine learning methods, demonstrating superior temporal dynamics crucial for solar forecasting.
- The research was published in the journal Solar Energy.
https://www.pv-magazine.com/2024/04/23/solar-forecasting-based-on-all-sky-imaging-long-short-term-memory/