A Wavelet–Attention–Convolution Hybrid Deep Learning Model for Accurate Short-Term Photovoltaic Power Forecasting

Kaoutar Ait Chaoui (), Hassan EL Fadil, Oumaima Choukai and Oumaima Ait Omar
Additional contact information
Kaoutar Ait Chaoui: ASE Laboratory, National School of Applied Sciences, Ibn Tofail University, Kenitra 14000, Morocco
Hassan EL Fadil: ASE Laboratory, National School of Applied Sciences, Ibn Tofail University, Kenitra 14000, Morocco
Oumaima Choukai: Higher National School of Chemistry—ENSC, Ibn Tofail University, Kenitra 14000, Morocco
Oumaima Ait Omar: ASE Laboratory, National School of Applied Sciences, Ibn Tofail University, Kenitra 14000, Morocco

Forecasting, 2025, vol. 7, issue 3, 1-29

Abstract: The accurate short-term forecasting (PV) of power is crucial for grid stability control, energy trading optimization, and renewable energy integration in smart grids. However, PV generation is extremely variable and non-linear due to environmental fluctuations, which challenge the conventional forecasting models. This study proposes a hybrid deep learning architecture, Wavelet Transform–Transformer–Temporal Convolutional Network–Efficient Channel Attention Network–Gated Recurrent Unit (WT–Transformer–TCN–ECANet–GRU), to capture the overall temporal complexity of PV data through integrating signal decomposition, global attention, local convolutional features, and temporal memory. The model begins by employing the Wavelet Transform (WT) to decompose the raw PV time series into multi-frequency components, thereby enhancing feature extraction and denoising. Long-term temporal dependencies are captured in a Transformer encoder, and a Temporal Convolutional Network (TCN) detects local features. Features are then adaptively recalibrated by an Efficient Channel Attention (ECANet) module and passed to a Gated Recurrent Unit (GRU) for sequence modeling. Multiscale learning, attention-driven robust filtering, and efficient encoding of temporality are enabled with the modular pipeline. We validate the model on a real-world, high-resolution dataset of a Moroccan university building comprising 95,885 five-min PV generation records. The model yielded the lowest error metrics among benchmark architectures with an MAE of 209.36, RMSE of 616.53, and an R 2 of 0.96884, outperforming LSTM, GRU, CNN-LSTM, and other hybrid deep learning models. These results suggest improved predictive accuracy and potential applicability for real-time grid operation integration, supporting applications such as energy dispatching, reserve management, and short-term load balancing.

Keywords: photovoltaic power forecasting; hybrid deep learning; wavelet transform; attention mechanism; transformer; ECANet; gated recurrent unit (GRU); temporal convolutional network (TCN); multiscale feature extraction; time series prediction (search for similar items in EconPapers)
JEL-codes: A1 B4 C0 C1 C2 C3 C4 C5 C8 M0 Q2 Q3 Q4 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2571-9394/7/3/45/pdf (application/pdf)
https://www.mdpi.com/2571-9394/7/3/45/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jforec:v:7:y:2025:i:3:p:45-:d:1727753

Access Statistics for this article

Forecasting is currently edited by Ms. Joss Chen

More articles in Forecasting from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().