Fourier-Enhanced Recurrent Neural Networks for Electrical Load Time Series Downscaling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915661851131904 |
|---|---|
| author | Chen, Qi Anitescu, Mihai |
| author_facet | Chen, Qi Anitescu, Mihai |
| contents | We present a Fourier-enhanced recurrent neural network (RNN) for downscaling electrical loads. The model combines (i) a recurrent backbone driven by low-resolution inputs, (ii) explicit Fourier seasonal embeddings fused in latent space, and (iii) a self-attention layer that captures dependencies among high-resolution components within each period. Across four PJM territories, the approach yields RMSE lower and flatter horizon-wise than classical Prophet baselines (with and without seasonality/LAA) and than RNN ablations without attention or Fourier features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07876 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fourier-Enhanced Recurrent Neural Networks for Electrical Load Time Series Downscaling Chen, Qi Anitescu, Mihai Machine Learning We present a Fourier-enhanced recurrent neural network (RNN) for downscaling electrical loads. The model combines (i) a recurrent backbone driven by low-resolution inputs, (ii) explicit Fourier seasonal embeddings fused in latent space, and (iii) a self-attention layer that captures dependencies among high-resolution components within each period. Across four PJM territories, the approach yields RMSE lower and flatter horizon-wise than classical Prophet baselines (with and without seasonality/LAA) and than RNN ablations without attention or Fourier features. |
| title | Fourier-Enhanced Recurrent Neural Networks for Electrical Load Time Series Downscaling |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.07876 |