yuhao-nie/SkyGPT
A physics-constrained stochastic sky video prediction model for probabilistic short-term solar forecasting
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.
Stars
63
Forks
11
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
FlexMeasures/flexmeasures
The intelligent & developer-friendly EMS to support real-time energy flexibility apps, rapidly...
ml-energy/zeus
Measure and optimize the energy consumption of your AI applications!
pyaf/load_forecasting
Forecasting electric power load of Delhi using ARIMA, RNN, LSTM, and GRU models
saizk/Deep-Learning-for-Solar-Panel-Recognition
CNN models for Solar Panel Detection and Segmentation in Aerial Images.
FateMurphy/CEEMDAN_LSTM
CEEMDAN_LSTM is a Python project for decomposition-integration forecasting models based on EMD...