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

2025/11/27 by Chen, Qi, Anitescu, Mihai
Computer Science · Engineering · Physics and Astronomy · #Energy Load and Power Forecasting #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Neural Networks and Reservoir Computing

paper · doi:10.48550/arxiv.2512.07876

openalex publication_date 2025/11/27 · openalex created_date 2025/12/11 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Forecasting at Scale
• Attention Is All You Need
• Layer Normalization
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• The Fourier Transform and its Applications.

Related

• Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study
• Sequence-to-Sequence Load Disaggregation Using Multi-Scale Residual Neural Network
• Contextually Enhanced ES-dRNN with Dynamic Attention for Short-Term Load Forecasting
• Short-Term Load Forecasting Using Time Pooling Deep Recurrent Neural\n Network
• ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting