The 4Cast company is dedicated to issue state-of-the art forecasts for power production from fluctuating sources which depend on weather conditions. Typically these are wind and solar power plants.
We use a bunch of weather data from services around the world as input source, together with the production data we apply BigData technology to learn the optimal model for short-term and long-term forecast
Using learning algorithms directly on the production data of the producer we can tune the 4cast models such that a minimal deviation occurs Our specialty is learning analytic models using symbolic regression, but of course the widely used deep learning networks are contained in our portfolio.
4casts without production data are typically worse, since local conditions like the earth's slope, neighbour plants, or the vegetation type cannot be included. Our learning algorithms do that job once production data are there, isn't that fantastic? Interested? Take a tour through our method with and without your data below!
Our basic model relies on the manufacturer's power curves. A coarse-grid weather prediction is mapped to the turbine spot.
The standard model is based on the manufacturer's power curves, your production data and a coarse-grid weather prediction. Our learning algorithm produces an improved parametrized power curve such that some local conditions are now included.
Based on your production data and a whole bunch of weather predictions, we let our machines learn an improved power curve. We choose the best model according to your specification. By increasing complexity, our learners include generalized linear regression, artificial neural networks, and symbolic regression.
Together with you we define customized targets which are fed into the learning algorithms to produce optimal forecast given your special needs.
An example is the generation of a forecast that maximizes your profit – this may differ from a best forecast of the production alone!