AI RESEARCH
Inpainting-Style Conditional Diffusion for Multivariable Time Series Forecasting
arXiv CS.CV
•
ArXi:2605.28324v1 Announce Type: new In this paper, we propose a novel conditional diffusion-based framework for multivariable time-series solar power forecasting. The proposed method reformulates temporal PV data as structured two-dimensional representations (images) using a sliding-window patch construction, enabling the application of Denoising Diffusion Probabilistic Models (DDPM) within a unified spatiotemporal learning paradigm.