A model to generate clear-sky index time-series in various locations

What is it about?

This model assumes that the sky is in one of three cloudiness states: cloudy, clear, and scattered clouds. The model then learns the probabilities of jumping between these cloudiness states. After learning these probabilities an infinite number of time-series can be generated to simulate the solar yield in a location.

Featured Image

Photo by Zbynek Burival on Unsplash

Photo by Zbynek Burival on Unsplash

Why is it important?

This model formally connected the physical and mathematical representations of the clear-sky models, which was not done previously.

Perspectives

“

It was a simple yet novel application of the hidden Markov models.

”