Benchmarking of Deep Learning Irradiance Forecasting Models from Sky Images -- an in-depth Analysis

TL;DR

This study benchmarks four deep learning models for short-term solar irradiance forecasting from sky images, revealing that while spatiotemporal encoding improves accuracy, models often behave similarly to persistence models and miss key cloud events.

Contribution

It provides a comprehensive comparison of deep learning architectures for sky image-based irradiance forecasting and highlights the limitations of current models in capturing cloud dynamics.

Findings

Spatiotemporal encoding improves forecast skill by 20.4%.

Deep learning models often behave like persistence models.

Models struggle to predict cloud-induced irradiance changes.

Abstract

A number of industrial applications, such as smart grids, power plant operation, hybrid system management or energy trading, could benefit from improved short-term solar forecasting, addressing the intermittent energy production from solar panels. However, current approaches to modelling the cloud cover dynamics from sky images still lack precision regarding the spatial configuration of clouds, their temporal dynamics and physical interactions with solar radiation. Benefiting from a growing number of large datasets, data driven methods are being developed to address these limitations with promising results. In this study, we compare four commonly used Deep Learning architectures trained to forecast solar irradiance from sequences of hemispherical sky images and exogenous variables. To assess the relative performance of each model, we used the Forecast Skill metric based on the smart persistence model, as well as ramp and time distortion metrics. The results show that encoding spatiotemporal aspects of the sequence of sky images greatly improved the predictions with 10 min ahead Forecast Skill reaching 20.4% on the test year. However, based on the experimental data, we conclude that, with a common setup, Deep Learning models tend to behave just as a 'very smart persistence model', temporally aligned with the persistence model while mitigating its most penalising errors. Thus, despite being captured by the sky cameras, models often miss fundamental events causing large irradiance changes such as clouds obscuring the sun. We hope that our work will contribute to a shift of this approach to irradiance forecasting, from reactive to anticipatory.