发表机构
RWTH Aachen University; Process Systems Engineering; Chair of Energy Efficient Buildings Indoor Climate（亚琛工业大学; 过程系统工程; 节能建筑室内气候主席席位）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究系统评估TabPFN-TS用于区域供热网络零样本概率热负荷预测，确定了最优配置，其性能接近Chronos-2且校准更好，相关发现推动了多分辨率残差校正预测器的开发。
AI 中文摘要
区域供热能源枢纽需要可靠的热负荷预测以实现高效的运行调度。传统的预测工作流程会基于历史数据训练特定于系统的模型，当网络因新增用户、设备改造或运行工况变化而发生改变时，这种方式会变得繁琐。零样本时间序列基础模型和上下文预测提供了一种有前景的替代方案：它们可在推理阶段根据近期观测值进行自适应调整，无需反复重新训练。本研究针对区域供热网络的概率热负荷预测任务，系统评估了TabPFN-TS与时间序列基础模型及已训练的机器学习基线模型的性能。与在大量真实时间序列上预训练的基础模型不同，TabPFN-TS依赖于合成预训练数据，这避免了预训练-测试的直接重叠，但引发了所学习的先验是否能捕捉区域供热动态的问题。我们在代表性运行周上分析了协变量选择、上下文长度、时间分辨率和预测 horizon，在一整年的数据上验证了所选配置，并在第二个网络上测试了可迁移性。结果表明，采用12周滚动上下文和环境温度的小时级24小时预测是简约且高性能的配置；更长的上下文窗口并未提升准确性。TabPFN-TS在确定性准确性上与Chronos-2接近，在主数据集上的CVRMSE值分别为13.06%和12.48%，在每日排名比较中处于临界差异阈值内。尽管Chronos-2实现了最低的全年总误差，但TabPFN-TS表现出更好的经验校准。最后，这些诊断发现推动了多分辨率残差校正预测器的开发，该模型结合了低频基础预测器和短 horizon 残差预测器，以提升更长 horizon 的规划准确性。
英文摘要
District heating energy hubs require reliable heat load forecasts for efficient operational scheduling. Forecasting models trained on historical data may require retraining as networks evolve. Zero-shot time-series foundation models and in-context forecasting therefore offer a promising alternative: they can adapt at inference time from recent observations rather than by repeated retraining. This study systematically evaluates TabPFN-TS and Chronos-2 for probabilistic heat load forecasting in two German district heating networks and compares them with trained baselines. We assess whether TabPFN-TS, whose underlying model is pretrained entirely on synthetic tabular rather than time-series data, can capture complex district heating dynamics. We analyze covariate choice, context length, temporal resolution, and forecast horizon on selected operating weeks, evaluate the selected configuration over the full year, and assess cross-network transfer. The principal benchmark assumes perfect weather forecasts; a separate sensitivity analysis uses retrospective weather predictions. Hourly 24-hour forecasting with a 12-week rolling context and ambient temperature provides a parsimonious configuration; longer context windows do not improve accuracy. Both TSFMs outperform all trained baselines in deterministic accuracy in the full-year benchmarks. Chronos-2 achieves the best deterministic scores, with TabPFN-TS remaining close: their CVRMSE values on the main data set are 12.48% and 13.07%, respectively. Chronos-2 also achieves lower continuous ranked probability scores in both networks, with TabPFN-TS remaining close. a TSFM-based Multi-Resolution Residual-Correction Forecaster combines an hourly base forecast with short-term high-resolution corrections. Relative to direct high-resolution forecasting, it generally reduces errors in total heat demand over 12-hour periods and recorded prediction times.
Comments43 pages, 10 figures; Supplementary Information included. Revised following peer review, with expanded evaluation and uncertainty analysis
