FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting

2026-08-06

AI Summary

This work addresses the critical need for high-accuracy intra-day solar irradiance forecasting—particularly the challenge of capturing abrupt irradiance ramps induced by rapid cloud dynamics—in grid-connected photovoltaic systems. To this end, we propose FarSky, a novel framework that, for the first time, integrates task-aware latent space coupling with a generative diffusion model. FarSky employs a multi-task autoencoder to learn a shared latent representation for sky image reconstruction and irradiance estimation, then leverages a conditional latent diffusion model to produce probabilistic forecasts of future irradiance. By jointly optimizing image semantics and prediction objectives within a unified architecture, FarSky significantly outperforms existing methods on two independent test sets, achieving up to an 11-percentage-point improvement in both deterministic and probabilistic forecast skill scores and exceeding 60% F1 score in detecting steep ramp events.

Abstract

Accurate solar irradiance forecasting is essential for the reliable integration of photovoltaic power into modern electricity grids. All-sky imagers (ASI) provide high-resolution observations of clouds, making them well suited for intra-hour forecasting. Recent deep learning approaches have substantially improved forecast accuracy but are often limited by deterministic predictions and a reduced capability to anticipate ramp events. This work proposes FarSky, a generative forecasting framework that leverages latent-space coupling to learn task-aware representations of sky images. A multi-task autoencoder first learns a shared latent representation for image reconstruction and irradiance estimation. A latent diffusion model then generates future latent states conditioned on recent observations, from which irradiance forecasts are directly decoded. Probabilistic forecasts are inherently obtained through stochastic sampling. The framework is developed using a multi-year ASI dataset acquired at the Plataforma Solar de Almería, Spain, and evaluated on two independent test datasets against persistence, state-of-the-art end-to-end, and generative forecasting approaches. FarSky achieves the best overall deterministic and probabilistic forecasting performance, improving forecast skill by up to 11 percentage points. Furthermore, it substantially improves ramp event detection over existing methods, achieving F1-scores above 60%. These results demonstrate the potential of combining generative models with task-aware latent-space coupling for solar forecasting.

Problem

• solar irradiance forecasting
• intra-hour forecasting
• ramp events
• probabilistic forecasting
• cloud dynamics

Innovation

• latent-space coupling
• generative forecasting
• multi-task autoencoder
• latent diffusion model
• intra-hour solar forecasting