RichardFindlay/day-ahead-probablistic-forecasting-with-quantile-regression

Using an integrated pinball-loss objective function in various recurrent based deep learning architectures made with keras to simultaneously produce probabilistic forecasts for UK wind, solar, demand and price forecasts.

27
/ 100
Experimental

This project helps energy analysts and traders accurately predict day-ahead electricity market conditions by providing probabilistic forecasts for UK wind and solar generation, electricity demand, and wholesale prices. It takes historical energy data as input and produces a range of possible future values, helping you understand the uncertainty in market movements.

No commits in the last 6 months.

Use this if you need to make informed decisions about energy trading or grid management by understanding the likely range of future energy supply and prices, not just a single predicted value.

Not ideal if you need a simple point forecast (a single predicted value) without considering the probability distribution, or if you are not working with UK energy market data.

energy-trading grid-management renewable-forecasting power-market-analysis energy-risk-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

43

Forks

5

Language

Python

License

Last pushed

Nov 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RichardFindlay/day-ahead-probablistic-forecasting-with-quantile-regression"

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