SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data

TL;DR

This paper introduces SunCast, a convolutional LSTM model for rapid, global-scale solar irradiance nowcasting that outperforms traditional NWP models in speed and maintains reasonable accuracy, aiding renewable energy management.

Contribution

The paper presents a novel, efficient deep learning model for short-term solar irradiance prediction on a global scale, with an accessible architecture and real-time capabilities.

Findings

Predicts solar irradiance up to 3 hours ahead for North America

Achieves RMSE of 120 W/m2 on two months of data

Operates in under 60 seconds on a single CPU without GPU

Abstract

When cloud layers cover photovoltaic (PV) panels, the amount of power the panels produce fluctuates rapidly. Therefore, to maintain enough energy on a power grid to match demand, utilities companies rely on reserve power sources that typically come from fossil fuels and therefore pollute the environment. Accurate short-term PV power prediction enables operators to maximize the amount of power obtained from PV panels and safely reduce the reserve energy needed from fossil fuel sources. While several studies have developed machine learning models to predict solar irradiance at specific PV generation facilities, little work has been done to model short-term solar irradiance on a global scale. Furthermore, models that have been developed are proprietary and have architectures that are not publicly available or rely on computationally demanding Numerical Weather Prediction (NWP) models. Here, we propose a Convolutional Long Short-Term Memory Network model that treats solar nowcasting as a next frame prediction problem, is more efficient than NWP models and has a straightforward, reproducible architecture. Our models can predict solar irradiance for entire North America for up to 3 hours in under 60 seconds on a single machine without a GPU and has a RMSE of 120 W/m2 when evaluated on 2 months of data.