发表机构
University of Cambridge（剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TRACE是一个可复现的电价预测基准，结合官方运行文本与价格数据，评估语义一致性并验证预测价值，上尾损失中位数降低7.4%。
AI 中文摘要
电价预测（EPF）支持电力市场中的调度、竞价和风险管理，然而现有基准主要侧重于数值输入，使得预测时点的文本上下文在预测中的价值未被充分评估。我们引入了TRACE，一个包含7,300个区域-日实例的可复现基准，这些实例将美国一个主要市场中五个区域的价格与预测截止时可获得的官方运行文本配对。TRACE在每个截止点重建官方运行文本，防止截止点后的信息泄漏。我们对TRACE进行了语义一致性和预测价值的评估。语义评估与真实价格中的中心变动及两个尾部风险一致，其中对价格上尾风险的评估最为一致。预测价值体现在时间序列基础模型上，上尾分位数损失中位数降低了7.4%。一项受控的跨日文本不匹配消融实验逆转了这些收益，使其低于无文本基线。
英文摘要
Electricity price forecasting (EPF) supports scheduling, bidding, and risk management in electricity markets, yet existing benchmarks focus mainly on numerical inputs, leaving the forecasting value of forecast-time textual context insufficiently evaluated. We introduce TRACE, a reproducible benchmark of 7,300 zone--day instances pairing prices from five zones in a major U.S. market with official operational text available at the forecast cutoff. TRACE reconstructs official operational text at each cutoff, preventing post-cutoff information leakage. We evaluate TRACE for semantic alignment and forecasting value. Semantic assessments align with central movement and both tail risks in ground-truth prices, most consistently for upper-tail price risk. Forecasting value is reflected in a median 7.4\% reduction in upper-tail pinball loss across time-series foundation models. A controlled cross-day text-mismatch ablation reverses the gains, falling below the no-text baseline.
CommentsAccepted to the NeurIPS 2026 Workshop on Foundation Models for Time Series (FMTS)
