arXiv:2512.07876cs.LGstat.ML2025-12

用傅里叶嵌入增强RNN,提升电力负荷时间序列的高分辨率下采样精度。

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

  • 结合低分辨率输入与傅里叶季节嵌入,增强时序建模能力
  • 在四个PJM区域测试中,均方根误差低于经典Prophet模型
  • 适合需要高精度电力负荷预测的能源系统研究者

我们提出一种傅里叶增强的循环神经网络(RNN),用于电力负荷时间序列的下采样。该模型包含:(i) 基于低分辨率输入的循环主干网络,(ii) 在隐空间融合的显式傅里叶季节嵌入,(iii) 自注意力层,用于捕捉每个周期内高分辨率分量间的依赖关系。在四个PJM区域的实验中,该方法的均方根误差(RMSE)低于经典Prophet基线模型(含与不含季节性/长短期平均项),且随预测时域变化更平稳,优于未加入注意力或傅里叶特征的RNN消融模型。

原文摘要 · Abstract (English)

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.

时间序列电力负荷RNN傅里叶

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。