Solar energy is predicted to be the largest form of power generation globally by 2040 and having accurate real-time forecasts is critical to anticipating power production. Unlike fossil fuels, renewable energies are unpredictable in terms of power generation from one hour to the next. In order to balance the grid, operators need an accurate daily estimate of when and how much PV and other renewable energies will be generated.

Open Climate Fix (OCF) is an open-source (OS) AI company using machine learning (ML) to respond to the need for accurate renewable energy forecasts. Connecting energy industry practitioners with ML researchers doing cutting-edge modelling is our aim, and one way we seek to do this is by making much of our code open-source (https://github.com/openclimatefix).

In the energy space, OCF’s first focus is on solar nowcasting (short-term forecasting). Our main deep learning model takes in real-time PV data, numeric weather predictions, satellite images, as well as regional grid data, and outputs probabilistic solar electricity nowcasts for solar production systems in the UK. What makes our approach unique is teaching cloud dynamics to the model using satellite data.

Our 36-hour forecast, Quartz Solar, is currently used by National Grid, the UK grid operator, as a decision-making tool in their control room. Building on this forecast, we are working on a new open-source model, Quartz Solar OS, that we want everyone (maybe FOSDEM attendees!), not just grid operators, to be able to use.

The talk OCF proposes will present the ML techniques used to develop Quartz Solar OS and the possible use cases and climate impact such a forecast could have. And yes, we’re hoping to have a demo!