Score: 0

Fourier-Enhanced Recurrent Neural Networks for Electrical Load Time Series Downscaling

Published: November 27, 2025 | arXiv ID: 2512.07876v1

By: Qi Chen, Mihai Anitescu

Potential Business Impact:

Predicts electricity use more accurately.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇺🇸 United States

Page Count
6 pages

Category
Computer Science:
Machine Learning (CS)