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

arXiv — stat.MLWednesday, December 10, 2025 at 5:00:00 AM
  • A new Fourier-enhanced recurrent neural network (RNN) has been developed for downscaling electrical loads, integrating low-resolution inputs with Fourier seasonal embeddings and a self-attention layer. This model has demonstrated lower and flatter RMSE across four PJM territories compared to traditional Prophet baselines and RNN variations lacking attention or Fourier features.
  • This advancement signifies a notable improvement in the accuracy of electrical load forecasting, which is crucial for energy management and planning, potentially leading to more efficient energy distribution and reduced operational costs in the power sector.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
Beyond Wave Variables: A Data-Driven Ensemble Approach for Enhanced Teleoperation Transparency and Stability
PositiveArtificial Intelligence
A new study introduces a data-driven ensemble approach to enhance transparency and stability in bilateral teleoperation systems, addressing challenges posed by communication delays. The framework replaces traditional wave-variable methods with advanced sequence models, including LSTM and CNN-LSTM, optimized through the Optuna algorithm. Experimental validation was conducted using Python, demonstrating the effectiveness of this innovative approach.