Sep 2026
A cluster-based short-term photovoltaic power forecasting method using K-means and CNN-BiLSTM-Attention
A clustering-based prediction framework that combines K-means clustering with a hybrid deep learning model that outperforms the baseline model on multiple error metrics is proposed, proving its effectiveness in predicting the power generation of multiple PV power plants.
Jian Tang, Lu-Lu Lin
· European Conference on Elect... · 0 citations