提出新评估框架，精准衡量电网负荷预测的失准风险。
Reliable Grid Forecasting: State Space Models for Safety-Critical Energy Systems
- 构建针对欠预测的可解释评估体系，突破传统误差指标局限。
- 发现模型MAPE相近但尾部备用需求差异显著，最大差超1700兆瓦。
- 揭示概率校准导致虚假安全，提出约束优化解决过度预报问题。
精准的电网负荷预测关乎安全：低估可能导致供电短缺，而对称误差指标会掩盖这种操作上的不对称性。本文引入可解释的评估框架——欠预测率（UPR）、99.5%分位尾部备用需求（Reserve_{99.5}^%）及显式偏差诊断（Bias_{24h}/OPR），量化单侧可靠性风险。在覆盖2023年11月至2025年11月共84,498条小时级数据的加州独立系统运营商（CAISO）多区域数据集上，采用滚动起源回测法，评估了五种神经架构：两种状态空间模型（S-Mamba、PowerMamba）、两种Transformer（iTransformer、PatchTST）、LSTM及一种概率性状态空间模型（Mamba-ProbTSF）。针对各模型归纳偏置设计了热滞后对齐的气象融合策略。结果表明，标准准确率指标无法反映运营安全性：不同模型虽具有相近的MAPE，但尾部备用需求差异显著。显式气象融合可缩小误差分布，改善幅度由模型架构决定——iTransformer的跨变量注意力受益更明显，优于PatchTST的通道独立结构。关键发现：风险规避型预测普遍存在‘虚假安全’现象——尽管概率校准降低上尾误差，但若无约束，会系统性抬高调度量（如严重情况下偏差增加超1,700兆瓦）。为此，本文提出基于偏差与欠预测率的约束目标，实现尾部风险最小化与避免冗余过估之间的可审计权衡。
原文摘要 · Abstract (English)
Accurate grid load forecasting is safety-critical: under-predictions risk supply shortfalls, while symmetric error metrics can mask this operational asymmetry. We introduce an operator-legible evaluation framework -- Under-Prediction Rate (UPR), tail $\text{Reserve}_{99.5}^{\%}$ requirements, and explicit inflation diagnostics ($\text{Bias}_{24h}$/OPR) -- to quantify one-sided reliability risk beyond MAPE. Using this framework, we evaluate five neural architectures -- two state space models (S-Mamba, PowerMamba), two Transformers (iTransformer, PatchTST), an LSTM, and a probabilistic SSM variant (Mamba-ProbTSF) -- on a weather-aligned California Independent System Operator (CAISO) dataset spanning Nov 2023--Nov 2025 (84,498 hourly records across 5 regional transmission areas) under a rolling-origin walk-forward backtest. We develop and evaluate thermal-lag-aligned weather fusion strategies matched to each architecture's inductive bias. Our results demonstrate that standard accuracy metrics are insufficient proxies for operational safety: models with comparable MAPE can imply materially different tail reserve requirements ($\text{Reserve}_{99.5}^{\%}$). We show that explicit weather integration narrows error distributions, with the magnitude of improvement being architecturally determined -- iTransformer's cross-variate attention benefits significantly more than PatchTST's channel-independent design. Crucially, we identify a widespread susceptibility to "fake safety" in risk-averse forecasting: while probabilistic calibration reduces upper-tail errors, it achieves this by systematically inflating schedules (e.g., increasing bias by over 1,700 MW in severe cases) if left unconstrained. To solve this, we introduce Bias/OPR-constrained objectives that enable auditable trade-offs between minimizing tail risk and preventing trivial over-forecasting.
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。