发表机构
Georgia Institute of Technology; Argonne National Laboratory（佐治亚理工学院; 阿贡国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OutageDiT是基于美国停电与天气记录训练的生成式基础模型，可生成15分钟分辨率的7天停电轨迹，能提升停电预测准确性与场景质量，支持零样本迁移及点预测、不确定性量化等功能。
AI 中文摘要
停电规划需要在事件发生前生成场景，这些场景必须能表征停电规模、发生时间和持续时间的不确定性，同时保留时间依赖性。然而，极端停电事件十分罕见，单个地区的数据中仅包含少量极端停电与恢复模式的示例。为解决这一挑战，我们提出OutageDiT，这是一个基于美国停电记录与天气记录训练的、可生成15分钟分辨率的7天停电轨迹的基础模型。具体而言，条件编码器在每次预测时处理一次历史上下文与已知未来协变量，浅层流解码器复用生成的与时间范围对齐的状态以生成完整轨迹。所得样本支持在单个深度生成模型内进行点预测、不确定性量化与条件事件模拟。在停电预测基准测试中，OutageDiT较强大的基线模型提升了预测准确性与场景质量，且支持对未见过地区的零样本迁移。综合来看，这些结果表明，条件停电模拟是从停电预测到不确定性下运营规划的桥梁。
英文摘要
Power-outage planning requires scenarios before an event occurs. These scenarios must represent uncertainty in magnitude, timing, and duration while preserving temporal dependence. However, severe events are rare, and data from any single region contain few examples of extreme outage and restoration patterns. To address this challenge, we introduce OutageDiT, a foundation model for generating seven-day outage trajectories at quarter-hour resolution, trained on outage and weather records across the United States. Specifically, a condition encoder processes the historical context and known future covariates once per forecast, and a shallow flow decoder reuses the resulting horizon-aligned states to generate complete trajectories. The resulting samples support point forecasting, uncertainty quantification, and conditional event simulation within one deep generative model. Across outage forecasting benchmarks, OutageDiT improves forecast accuracy and scenario quality over strong baselines and supports zero-shot transfer to held-out regions. Together, these results position conditional outage simulation as a bridge from outage forecasting to operational planning under uncertainty.
Comments10 pages, 2 figures, 3 tables
