# A deep learning approach to solar-irradiance forecasting in sky-videos

## TL;DR

This paper introduces a deep learning method using sky-videos from inexpensive cameras to accurately forecast short-term solar irradiance, outperforming traditional satellite-based models in error reduction.

## Contribution

The study presents a novel deep neural network approach for direct solar irradiance forecasting from sky-videos, utilizing large publicly available datasets from North American weather stations.

## Key findings

- Significant error reduction compared to satellite models.
- Effective short-term (up to 4 hours) irradiance forecasting.
- Largest dataset of sky-videos for this application to date.

## Abstract

Ahead-of-time forecasting of incident solar-irradiance on a panel is indicative of expected energy yield and is essential for efficient grid distribution and planning. Traditionally, these forecasts are based on meteorological physics models whose parameters are tuned by coarse-grained radiometric tiles sensed from geo-satellites. This research presents a novel application of deep neural network approach to observe and estimate short-term weather effects from videos. Specifically, we use time-lapsed videos (sky-videos) obtained from upward facing wide-lensed cameras (sky-cameras) to directly estimate and forecast solar irradiance. We introduce and present results on two large publicly available datasets obtained from weather stations in two regions of North America using relatively inexpensive optical hardware. These datasets contain over a million images that span for 1 and 12 years respectively, the largest such collection to our knowledge. Compared to satellite based approaches, the proposed deep learning approach significantly reduces the normalized mean-absolute-percentage error for both nowcasting, i.e. prediction of the solar irradiance at the instance the frame is captured, as well as forecasting, ahead-of-time irradiance prediction for a duration for upto 4 hours.