Publication Date




Solar energy is now the cheapest form of electricity in history. Unfortunately,

signi.cantly increasing the electric grid’s fraction of

solar energy remains challenging due to its variability, which makes

balancing electricity’s supply and demand more di.cult. While

thermal generators’ ramp rate—the maximum rate at which they

can change their energy generation—is .nite, solar energy’s ramp

rate is essentially in.nite. Thus, accurate near-term solar forecasting,

or nowcasting, is important to provide advance warnings to

adjust thermal generator output in response to variations in solar

generation to ensure a balanced supply and demand. To address the

problem, this paper develops a general model for solar nowcasting

from abundant and readily available multispectral satellite data

using self-supervised learning.

Speci.cally, we develop deep auto-regressive models using convolutional

neural networks (CNN) and long short-term memory

networks (LSTM) that are globally trained across multiple locations

to predict raw future observations of the spatio-temporal spectral

data collected by the recently launched GOES-R series of satellites.

Our model estimates a location’s near-term future solar irradiance

based on satellite observations, which we feed to a regression model

trained on smaller site-speci.c solar data to provide near-term solar

photovoltaic (PV) forecasts that account for site-speci.c characteristics.

We evaluate our approach for di.erent coverage areas and

forecast horizons across 25 solar sites and show that it yields errors

close to that of a model using ground-truth observations.

Journal or Book Title

e-Energy '22: Proceedings of the Thirteenth ACM International Conference on Future Energy Systems