yuhao-nie/SkyGPT

A physics-constrained stochastic sky video prediction model for probabilistic short-term solar forecasting

40
/ 100
Emerging

Effectively managing renewable energy grids requires accurate short-term solar power forecasts. This project helps solar farm operators and energy grid managers predict future solar power output by analyzing historical sky images to generate potential future sky videos. These videos then inform a probabilistic forecast of solar photovoltaic (PV) output, helping you anticipate fluctuations caused by changing cloud conditions.

No commits in the last 6 months.

Use this if you need to generate reliable, probabilistic 15-minute-ahead forecasts of solar photovoltaic (PV) power output based on real-time sky conditions.

Not ideal if you need long-term solar forecasts or are not working with sky image data for your predictions.

solar-forecasting renewable-energy-management grid-stability energy-trading power-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

63

Forks

11

Language

Jupyter Notebook

License

MIT

Last pushed

May 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuhao-nie/SkyGPT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.