OutageDiT：面向停电预测与场景生成的基础模型

View PDF HTML (experimental)

Abstract: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 15-minute resolution, trained on outage and weather records across the United States. Specifically, a condition encoder processes historical context and known future covariates once per forecast, and a shallow flow-matching decoder reuses the resulting horizon-aligned states to sample complete outage trajectories. This enables point forecasting, uncertainty quantification, and conditional scenario generation 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 scenario generation as a bridge from outage forecasting to operational planning under uncertainty.

Comments:	11 pages, 3 figures, 3 tables. Accepted at the NeurIPS 2026 Second Workshop on MLxOR
Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2609.01896 [cs.LG]
	(or arXiv:2609.01896v2 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2609.01896 arXiv-issued DOI via DataCite

Submission history

From: Yunqin Zhu [view email]
[v1] Tue, 1 Sep 2026 21:54:17 UTC (172 KB)
[v2] Tue, 27 Oct 2026 21:59:08 UTC (357 KB)