National Grid turns to AI for improved solar power forecasts

It worked with The Alan Turing Institute to develop the AI prediction methods that have so far helped deliver a 33% improvement in solar forecasting

National Grid Electricity System Operator (ESO) has turned to artificial intelligence (AI) and machine learning to help improve forecasts from solar panels and wind turbines in the UK.

It joined forces with The Alan Turing Institute to develop the AI prediction methods that have so far helped deliver a 33% improvement in solar forecasting.

Accurate forecasting of intermittent solar and wind generation through the joint project – funded by the Ofgem Network Innovation Allowance (NIA) – allows National Grid ESO to help operate the system “economically and efficiently” as it has set out to operate a zero carbon electricity grid by 2025.

The new system looks at historic data and around 80 input variables, including temperature and trains itself by finding hundreds of different mathematical pathways to take those inputs and arrive at the output generation figure.

It is then tested again against the 80 new weather forecasts to give the new solar generation forecast.

Rob Rome, Commercial Operations Manager at the ESO said it is vital for its forecasts to be as accurate as possible as renewable energy sources are becoming a bigger part of the energy mix.

He added: “The ESO’s dedicated innovation team are always looking at new techniques and methods to help us balance the system and this partnership with The Alan Turing Institute is a great example.

“Improved solar forecasts will help us run the system more efficiently, ultimately meaning lower bills for consumers. It will also enable more solar capacity to be connected and utilised, helping us to achieve our 2025 ambition to be able to operate a zero carbon electricity system.”

Latest Podcast