arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.10848cs.LGcs.AI
收藏

用于消费者硬件的能源负载预测时间序列基础模型:一个多维零样本基准

Time Series Foundation Models for Energy Load Forecasting on Consumer Hardware: A Multi-Dimensional Zero-Shot Benchmark

Independent Researcher, Turin, Italy(独立研究者, 意大利都灵)

Luigi Simeone

AI总结:

本文提出一个多维零样本基准,评估了四种时间序列基础模型在能源负载预测中的表现,揭示了预训练模型在准确性、校准和鲁棒性上的优势。

摘要:

时间序列基础模型(TSFMs)引入了零样本预测能力,从而绕过了任务特定训练的需要。这些能力是否能转化为关键应用,如电力需求预测——其中准确性、校准性和鲁棒性直接影响电网运行——仍然是一个开放性问题。我们提出一个多维基准,评估了四个TSFMs(Chronos-Bolt、Chronos-2、Moirai-2和TinyTimeMixer)以及Prophet作为行业标准基线和两个统计参考(SARIMA和Seasonal Naive),使用ERCOT 2020至2024年的每小时负载数据。所有实验均在消费者级硬件(AMD Ryzen 7,16GB RAM,无GPU)上运行。评估涵盖四个轴:(1)从24到2048小时的上下文长度敏感性,(2)概率预测校准,(3)在分布变化下的鲁棒性,包括新冠 lockdowns和Winter Storm Uri,以及(4)用于操作决策支持的预测性分析。表现最佳的基础模型在长上下文长度(C=2048小时,日提前期)下达到MASE值接近0.31,比Seasonal Naive基线减少了47%。Prophet的引入揭示了预训练模型的结构优势:当拟合窗口短于其季节性周期时,Prophet失败(MASE>74在24小时上下文),而TSFMs在最小上下文下仍能保持稳定的准确性,因为它们在预训练中学习了时间模式,而不是从头估计。校准在不同模型中变化显著——Chronos-2产生良好的预测区间(95%经验覆盖在90%名义水平)而Moirai-2和Prophet表现出过度自信(~70%覆盖)。我们提供了实用的模型选择指南,并释放了完整的基准框架以确保可重复性。

英文摘要:

Time Series Foundation Models (TSFMs) have introduced zero-shot prediction capabilities that bypass the need for task-specific training. Whether these capabilities translate to mission-critical applications such as electricity demand forecasting--where accuracy, calibration, and robustness directly affect grid operations--remains an open question. We present a multi-dimensional benchmark evaluating four TSFMs (Chronos-Bolt, Chronos-2, Moirai-2, and TinyTimeMixer) alongside Prophet as an industry-standard baseline and two statistical references (SARIMA and Seasonal Naive), using ERCOT hourly load data from 2020 to 2024. All experiments run on consumer-grade hardware (AMD Ryzen 7, 16GB RAM, no GPU). The evaluation spans four axes: (1) context length sensitivity from 24 to 2048 hours, (2) probabilistic forecast calibration, (3) robustness under distribution shifts including COVID-19 lockdowns and Winter Storm Uri, and (4) prescriptive analytics for operational decision support. The top-performing foundation models achieve MASE values near 0.31 at long context lengths (C = 2048h, day-ahead horizon), a 47% reduction over the Seasonal Naive baseline. The inclusion of Prophet exposes a structural advantage of pre-trained models: Prophet fails when the fitting window is shorter than its seasonality period (MASE > 74 at 24-hour context), while TSFMs maintain stable accuracy even with minimal context because they recognise temporal patterns learned during pre-training rather than estimating them from scratch. Calibration varies substantially across models--Chronos-2 produces well-calibrated prediction intervals (95% empirical coverage at 90% nominal level) while both Moirai-2 and Prophet exhibit overconfidence (~70% coverage). We provide practical model selection guidelines and release the complete benchmark framework for reproducibility.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑