Unlike fossil fuels, renewable energy is unpredictable in terms of power generation from one hour to the next. In order to maximise the utility of solar energy in the home and industry, being able to predict the generation coming in the next hour or day will allow smart homes to choose when to charge an EV, run a home appliance or cycle a heat pump.

OCF’s first focus is on solar short-term forecasting. Our most advanced AI 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 in the UK.

The talk OCF proposes will present the ML techniques used to develop Quartz Solar OS. It currently has a single-model architecture implemented and trained.

The talk will further delve into the enhancements Rosheen Naeem is working on as part of her Google Summer of Code project, which focuses on adding more model architectures. The models would be trained on publicly available weather data and a PV generation dataset that is already made publicly available.

The talk will also cover the possible use cases and climate impact such a forecast could have.