Solar power forecasting using domain knowledge

• Published in: Energy (Oxford) Vol. 302; p. 131709
• Main Authors: Mondal, Rakesh, Roy, Surajit Kr, Giri, Chandan
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-09-2024
• Subjects: Deep learning; Energy; Machine learning; Solar power prediction; Deep learning; Solar power prediction; Energy; PV; Machine learning
• ISSN: 0360-5442
• DOI: 10.1016/j.energy.2024.131709

Integrating renewable energy into the existing energy market is crucial. Solar power forecasting is essential since it depends on weather parameters and must integrate with the central grid to use the produced solar power effectively. Contemporary studies indicate that machine learning has the potential to predict the future generation of solar energy based on past data. This research demonstrates a broad range of solar power forecasting, combining the one-year time series solar power generation data, solar panel physical features, and weather information with the help of machine learning and deep learning tools with domain knowledge. The dataset is curated and preprocessed. We propose a deep learning ensemble model based on BI-LSTM. The proposed model can forecast well regardless of geographical position and is able to predict both short-term and long-term time horizons. We compared the results of the proposed model with the existing dataset and multiple standard deep learning models and found that our model produced better performance than traditional models. We also validated our model using different solar plants in Durgapur, India. For long-term forecasting, our model also outperformed the base model.
•We propose a unique solar power forecasting model using BI-LSTM Ensemble.•Prepared dataset combines the features of solar panels and meteorological data.•Our model can predict solar power generation in both short and long time horizons.•Our model produces results with reasonable accuracy.