基于学习的概率性负荷预测：事后与模型内不确定性
Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty
浏览论文内容
中文总结 AI 辅助
研究智能建筑负荷预测中，推理输入重建后不确定性放置问题。开发统一概率预测框架，比较模块化事后与集成模型内分位数学习方案，用三种深度学习骨干模型实验，发现不确定性放置依赖骨干模型，揭示事后残差分位数局限性。
中文摘要 AI 辅助
智能建筑负荷预测器通常在密集、多变量、高频数据上进行离线训练，但部署时可能仅提供每小时的、特征有限的输入。缺失特征必须重建，其误差会在模型中传播。若未反映这种输入不确定性，预测区间可能校准错误，影响需求响应调度。本文研究推理输入重建后不确定性的放置位置。开发了一个统一的提前一天概率预测框架，该框架对齐时间分辨率、重建不可用输入并推导因果特征，比较了模块化事后残差分位数方案与集成模型内分位数学习方案。使用三种中规模深度学习骨干模型进行比较，结果表明不确定性放置依赖于骨干模型。集成分位数学习在TFT模型中最可靠，在标记测试窗口上产生2.2 - 3.6%的平均绝对百分比误差和28 - 83W的均方根误差，同时在最接近标称覆盖水平时产生的区间比模块化区间窄约5倍。Diebold - Mariano检验支持TFT的排名和循环骨干模型的混合行为。重建敏感性测试表明，重建输入使分位数得分提高106%，而区间宽度几乎不变，表明模型不会自动吸收重建引起的不确定性。针对非深度学习基线和季节性留出周的稳健性检查支持这一排名。我们的结果揭示了推理依赖于重建输入时事后残差分位数的局限性。
英文摘要
Smart-building load forecasters are often trained offline on dense, multivariate, high-frequency data, but deployment may provide only hourly, feature-limited inputs. Missing features must then be reconstructed, and their errors can propagate through the model. If this input uncertainty is not reflected, prediction intervals may become miscalibrated, affecting demand-response scheduling. Our work examines where uncertainty should be placed once inference inputs are reconstructed. We develop a unified one-day-ahead probabilistic forecasting framework that aligns temporal resolution, reconstructs the unavailable inputs, and derives causal features, and we compare a modular post-hoc residual-quantile scheme with an integrated in-model quantile-learning scheme. The comparison uses three mid-scale Deep Learning (DL) backbones: recurrent, hybrid recurrent, and attention-based Temporal Fusion Transformer (TFT) models, under identical inputs, forecasting horizon, preprocessing rules, and training budgets. Results show that uncertainty placement is backbone-dependent. Integrated quantile learning is most reliable with the TFT, yielding 2.2-3.6% MAPE and 28-83W RMSE on the labeled test window, while producing intervals about 5x narrower than the modular intervals at the closest-to-nominal coverage level. Diebold-Mariano tests support the TFT ranking and the mixed behavior of the recurrent backbones. A reconstruction-sensitivity test shows that reconstructed inputs increase the Quantile Score (QS) by 106% while interval width remains nearly unchanged, indicating that the model does not automatically absorb reconstruction-induced uncertainty. Robustness checks against non-DL baselines and seasonal hold-out weeks support this ranking. Our results expose the limits of post-hoc residual quantiles when inference depends on reconstructed inputs.
发表机构
- Istanbul Technical University（伊斯坦布尔技术大学）
机构由 AI 辅助整理，请以论文原文为准。
