一种用于短期负荷预测的轻量级多视角方法
A Lightweight Multi-View Approach to Short-Term Load Forecasting
AI 导读
一篇 arXiv 论文提出一种用于短期负荷预测的轻量级多视角方法，利用单值嵌入和缩放的时间范围输入来高效捕捉时间相关特征。该方法引入嵌入 dropout 机制，防止过度依赖特定特征并增强可解释性。它以显著更少的参数实现有竞争力的性能，在含噪声或稀疏数据的多个数据集上表现稳健。
正文 · 原文
Abstract:Time series forecasting is a critical task across domains such as energy, finance, and meteorology, where accurate predictions enable informed decision-making. While transformer-based and large-parameter models have recently achieved state-of-the-art results, their complexity can lead to overfitting and unstable forecasts, especially when older data points become less relevant. In this paper, we propose a lightweight multi-view approach to short-term load forecasting that leverages single-value embeddings and a scaled time-range input to capture temporally relevant features efficiently. We introduce an embedding dropout mechanism to prevent over-reliance on specific features and enhance interpretability. Our method achieves competitive performance with significantly fewer parameters, demonstrating robustness across multiple datasets, including scenarios with noisy or sparse data, and provides insights into the contributions of individual features to the forecast.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.09220 [cs.LG] |
| (or arXiv:2602.09220v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.09220 arXiv-issued DOI via DataCite |
Submission history
From: Julien Guité-Vinet [view email]
[v1]
Mon, 9 Feb 2026 21:43:42 UTC (1,804 KB)
[v2]
Tue, 3 Nov 2026 23:30:20 UTC (5,501 KB)
来源：arXiv cs.AI · arxiv.org