Skip to content
Sagan

Paper

Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series

Unreadunread

AI summary

arXiv:2606. 24955v1 Announce Type: new Abstract: Power forecasting models deployed in real-world energy markets must operate under nonstationary conditions, where data distributions continually evolve due to weather variability, infrastructure upgrades, and changing consumption behaviors.