Short-term photovoltaic power prediction model based on hierarchical clustering of K-means++ algorithm and deep learning hybrid model DOI
Man Wang, Xiaojing Ma, Ru Wang

et al.

Journal of Renewable and Sustainable Energy, Journal Year: 2024, Volume and Issue: 16(2)

Published: March 1, 2024

In order to further improve the accuracy of photovoltaic (PV) power prediction and stability system, a short-term PV model based on hierarchical clustering K-means++ algorithm deep learning hybrid is proposed in this paper. First, used cluster historical data into different weather scenes according seasons. Second, combining convolutional neural network (CNN), squeeze-and-excitation attention mechanism (SEAM), bidirectional long memory (BILSTM) constructed capture long-term dependencies time series, improved pelican optimization (IPOA) optimize hyperparameters model. Finally, an example for modeling analysis conducted by using actual output meteorological station Ili region Xinjiang, China. The effectiveness are verified comparing with LSTM, BILSTM, CNN-BILSTM, POA-CNN-SEAM-BILSTM models, superiority IPOA particle swarm whale algorithm. results show that can obtain better under seasons, optimized improved.

Language: Английский

Harnessing AI for solar energy: Emergence of transformer models DOI
Muhammad Fainan Hanif, Jianchun Mi

Applied Energy, Journal Year: 2024, Volume and Issue: 369, P. 123541 - 123541

Published: June 1, 2024

Language: Английский

Citations

11
Short-term photovoltaic power prediction model based on hierarchical clustering of K-means++ algorithm and deep learning hybrid model DOI
Man Wang, Xiaojing Ma, Ru Wang

et al.

Journal of Renewable and Sustainable Energy, Journal Year: 2024, Volume and Issue: 16(2)

Published: March 1, 2024

In order to further improve the accuracy of photovoltaic (PV) power prediction and stability system, a short-term PV model based on hierarchical clustering K-means++ algorithm deep learning hybrid is proposed in this paper. First, used cluster historical data into different weather scenes according seasons. Second, combining convolutional neural network (CNN), squeeze-and-excitation attention mechanism (SEAM), bidirectional long memory (BILSTM) constructed capture long-term dependencies time series, improved pelican optimization (IPOA) optimize hyperparameters model. Finally, an example for modeling analysis conducted by using actual output meteorological station Ili region Xinjiang, China. The effectiveness are verified comparing with LSTM, BILSTM, CNN-BILSTM, POA-CNN-SEAM-BILSTM models, superiority IPOA particle swarm whale algorithm. results show that can obtain better under seasons, optimized improved.

Language: Английский

Citations

6