对比6种预训练时序模型在电价预测中的表现，发现传统方法仍更稳定。
Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting
- 用6个预训练时序模型对比经典统计与机器学习方法
- 德国等五国日间电价预测中，传统MSTL模型表现最佳
- 无预训练模型显著优于传统方法，但部分模型性能接近
精准的电力价格预测（EPF）对现货市场交易决策至关重要。尽管生成式人工智能和预训练大语言模型推动了多种时序基础模型（TSFMs）的发展，其在电价预测中的有效性尚不明确。为此，我们以德国、法国、荷兰、奥地利和比利时2024年日前拍卖（DAA）电价数据为基准，评估了Chronos-Bolt、Chronos-T5、TimesFM、Moirai、Time-MoE和TimeGPT六种先进预训练模型，与传统统计及机器学习方法在一天期预测任务上的表现。结果表明，Chronos-Bolt与Time-MoE在预训练模型中表现最强，与传统模型相当；但具有双周期季节性建模能力的biseasonal MSTL模型在各国及各项指标上均表现稳健，无任何TSFM在统计上显著超越它。
原文摘要 · Abstract (English)
Accurate electricity price forecasting (EPF) is crucial for effective decision-making in power trading on the spot market. While recent advances in generative artificial intelligence (GenAI) and pre-trained large language models (LLMs) have inspired the development of numerous time series foundation models (TSFMs) for time series forecasting, their effectiveness in EPF remains uncertain. To address this gap, we benchmark several state-of-the-art pretrained models--Chronos-Bolt, Chronos-T5, TimesFM, Moirai, Time-MoE, and TimeGPT--against established statistical and machine learning (ML) methods for EPF. Using 2024 day-ahead auction (DAA) electricity prices from Germany, France, the Netherlands, Austria, and Belgium, we generate daily forecasts with a one-day horizon. Chronos-Bolt and Time-MoE emerge as the strongest among the TSFMs, performing on par with traditional models. However, the biseasonal MSTL model, which captures daily and weekly seasonality, stands out for its consistent performance across countries and evaluation metrics, with no TSFM statistically outperforming it.
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。