.png){kind=icon}
.png){kind=icon}
Return
Long-term industrial electricity forecasting using generative adversarial networks and deep learning
.png){kind=icon}
PRE
AI
D
D
N
DOI：10.1016/j.cie.2025.111791.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A Conditional Generative Adversarial Network-based model is developed for industrial electricity forecasting. • Long-short-term memory networks are integrated into both Generator and Discriminator, replacing conventional Convolutional Neural Networks. • Wavelet decomposition separates data into trend, seasonal, and residual components, enabling the model to address specific patterns in each data type. • Modified neural networks for each component improve forecasting accuracy and computational efficiency by optimizing neural attributes based on the characteristics of each decomposed element. • The model demonstrates enhanced prediction performance across short- and long-term horizons.
Journal
IF:
6.5
Papers:
1.0W
Citations:
3.8W
Organization
No organization information available
Cited Papers