用可学习的分解方法提升电力需求预测精度，避免时间信息泄露。
VMDNet: Temporal Leakage-Free Variational Mode Decomposition for Electricity Demand Forecasting
- 对每条样本独立做VMD分解，防止时间数据泄露。
- 通过频率感知嵌入和并行卷积网络实现各模式独立建模，提升效率。
- 设计双层博弈机制自动优化关键超参数，适合电力预测场景。
准确的电力需求预测面临现实需求序列强多周期性的挑战，有效建模重复时间模式至关重要。分解技术能显式揭示此类结构，从而提升预测性能。变分模态分解（VMD）是一种具备周期性感知能力的信号处理方法，近年来应用日益广泛。然而，现有研究常存在信息泄露问题，且依赖不当的超参数调优。为此，我们提出VMDNet，一种保持因果关系的框架：(i) 采用逐样本VMD以避免时间泄漏；(ii) 用频率感知嵌入表示每个分解模态，并通过并行时间卷积网络（TCNs）解码，确保模态独立性与高效学习；(iii) 引入受斯塔克尔伯格博弈启发的双层优化方案，指导VMD两个关键超参数的选择。在三个常用电力需求数据集上的实验表明，VMDNet持续优于当前最优基线。
原文摘要 · Abstract (English)
Accurate electricity demand forecasting is challenging due to the strong multi-periodicity of real-world demand series, which makes effective modeling of recurrent temporal patterns crucial. Decomposition techniques make such structure explicit and thereby improve predictive performance. Variational Mode Decomposition (VMD) is a powerful signal-processing method for periodicity-aware decomposition and has seen growing adoption in recent years. However, existing studies often suffer from information leakage and rely on inappropriate hyperparameter tuning. To address these issues, we propose VMDNet, a causality-preserving framework that (i) applies sample-wise VMD to avoid temporal leakage; (ii) represents each decomposed mode with frequency-aware embeddings and decodes it using parallel temporal convolutional networks (TCNs), ensuring mode independence and efficient learning; and (iii) introduces a Stackelberg game inspired bilevel scheme to guide the selection of VMD's two key hyperparameters. Experiments on three widely used electricity demand datasets show that VMDNet consistently outperforms state-of-the-art baselines.
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。