发表机构
University of California, Santa Cruz（加州大学圣克鲁兹分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对协变量不确定性下的短期负荷预测，基准测试了四种从头训练模型和四种时间序列基础模型，发现Chronos-2在协变量准确时最优，而TimesNet在严重不确定性下更鲁棒。
AI 中文摘要
准确的短期负荷预测（STLF）对于现代电力系统的可靠高效运行至关重要。尽管时间序列基础模型（TSFMs）近期在广泛的预测任务中展现出卓越性能，但其在现实运行条件下用于短期负荷预测的有效性仍未得到充分探索。本文在三个真实世界负荷预测数据集上，针对未来协变量信息的可用性和质量不同的运行场景，对四种从头训练（TFS）模型和四种时间序列基础模型进行了全面基准测试。结果表明，在未来协变量可用或预测准确的情况下，Chronos-2在零样本和微调设置中均持续达到最先进性能。然而，随着协变量预测噪声增大，其性能下降，而TimesNet在严重协变量不确定性下表现出更强的鲁棒性。这些发现证明了协变量感知的时间序列基础模型在短期负荷预测中的有效性，同时凸显了稳健协变量建模在现实预测应用中的关键作用。
英文摘要
Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation models (TSFMs) have recently demonstrated remarkable performance across a wide range of forecasting tasks, their effectiveness for STLF under realistic operational conditions remains largely unexplored. In this paper, we present a comprehensive benchmark of four trained-from-scratch (TFS) models and four TSFMs across three real-world load forecasting datasets under operational scenarios that differ in the availability and quality of future covariate information. Our results show that Chronos-2 consistently achieves state-of-the-art performance in both zero-shot and fine-tuned settings when future covariates are available or accurately forecast. However, its performance degrades as covariate forecasts become increasingly noisy, whereas TimesNet exhibits greater robustness under severe covariate uncertainty. These findings demonstrate the effectiveness of covariate-informed TSFMs for STLF while highlighting the critical role of robust covariate modeling in real-world forecasting applications.
Comments5 pages, 1 figure, 5 tables. Accepted to the 2027 IEEE PES Grid Edge Conference & Expo, Salt Lake City, UT, USA, 19-22 April 2027
