Systematic Evaluation of TabPFN-TS for Zero-Shot Probabilistic Heat Load Forecasting in District Heating Networks

📄 arXiv: 2608.20024v1 📥 PDF

作者: Ben Spoek, Karim K. Ben Hicham, Kai Derzsi, Philipp Althaus, Alexander Mitsos, Dirk Müller

分类: cs.LG

发布日期: 2026-08-20

备注: 33 pages, 10 figures; supplementary information included


💡 一句话要点

提出TabPFN-TS以解决区域供热网络的零-shot热负荷预测问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 热负荷预测 区域供热 零-shot学习 时间序列模型 机器学习 概率预测 能源管理

📋 核心要点

  1. 现有的热负荷预测方法依赖于历史数据训练特定模型,难以适应网络变化。
  2. 论文提出TabPFN-TS模型,通过零-shot学习和上下文预测,避免了重复训练的需求。
  3. 实验结果显示,TabPFN-TS在确定性准确性上接近Chronos-2,且在经验校准上表现更佳。

📝 摘要(中文)

区域供热能源中心需要可靠的热负荷预测以实现高效的运营调度。传统的预测工作流程依赖于历史数据训练特定模型,但在网络因新用户、改造或操作模式变化而变化时,这种方法显得繁琐。零-shot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,它们可以在推理时从最近的观察中适应,而无需反复重训练。本研究系统性地评估了TabPFN-TS在区域供热网络中进行概率热负荷预测的表现,结果表明,使用12周的滚动上下文和环境温度的每小时24小时预测配置表现优异,且TabPFN-TS在确定性准确性上接近Chronos-2。

🔬 方法详解

问题定义:本论文旨在解决区域供热网络中热负荷预测的准确性和适应性问题。现有方法在网络结构变化时需要频繁重训练,导致效率低下。

核心思路:论文提出的TabPFN-TS模型利用零-shot学习和上下文预测,能够在推理阶段根据最近的观察进行适应,而无需依赖于历史数据的重训练。

技术框架:该方法的整体架构包括数据预处理、模型训练和推理三个主要阶段。首先,使用合成数据进行预训练,然后在推理时结合最新的观测数据进行预测。

关键创新:TabPFN-TS的主要创新在于其使用合成数据进行预训练,避免了传统方法中预训练与测试数据的重叠问题,同时保持了对区域供热动态的捕捉能力。

关键设计:在参数设置上,论文选择了12周的滚动上下文和环境温度作为输入特征,采用了特定的损失函数以优化预测准确性。

🖼️ 关键图片

fig_0
img_1
img_2

📊 实验亮点

实验结果表明,TabPFN-TS在主要数据集上的CVRMSE值为13.06%,接近Chronos-2的12.48%。尽管Chronos-2在全年的总误差上最低,但TabPFN-TS在经验校准方面表现更佳,显示出其在实际应用中的优势。

🎯 应用场景

该研究的潜在应用领域包括区域供热系统的运营调度和能源管理。通过提高热负荷预测的准确性,能够有效降低能源浪费,提升系统的整体效率,具有重要的实际价值和未来影响。

📄 摘要(原文)

District heating energy hubs require reliable heat load forecasts for efficient operational scheduling. Conventional forecasting workflows train system-specific models on historical data, which can become burdensome when networks change through new consumers, retrofits, or changing operating regimes. Zero-shot time-series foundation models and in-context forecasting offer a promising alternative: they can adapt at inference time from recent observations rather than by repeated retraining. This study systematically evaluates TabPFN-TS against time-series foundation models and trained machine-learning baselines for probabilistic heat load forecasting in district heating networks. Unlike foundation models pretrained on large collections of real time series, TabPFN-TS relies on synthetic pretraining data, which avoids direct pretraining-test overlap but raises the question of whether the learned prior captures district heating dynamics. We analyze covariate choice, context length, temporal resolution, and prediction horizon on representative operating weeks, validate the selected configuration over a full year, and test transferability on a second network. The results identify hourly 24-hour forecasting with a 12-week rolling context and ambient temperature as a parsimonious high-performing configuration; longer context windows do not improve accuracy. TabPFN-TS remains close to Chronos-2 in deterministic accuracy, reaching CVRMSE values of 13.06% versus 12.48% on the main dataset, and lies within the critical-difference threshold in the daily-rank comparison. Although Chronos-2 achieves the lowest aggregate full-year error, TabPFN-TS shows better empirical calibration. Finally, the diagnostic findings motivate a Multi-Resolution Residual-Correction Forecaster that combines a low-frequency Base Forecaster with a short-horizon Residual Forecaster to improve longer-horizon planning accuracy.