Standard content for Members only
To continue reading this article, please login to your Utility Week account, Start 14 day trial or Become a member.
If your organisation already has a corporate membership and you haven’t activated it simply follow the register link below. Check here.
Machine learning has helped the electricity system operator (ESO) at National Grid to improve the accuracy of its solar forecasts by a third as part of a joint initiative with the Alan Turing Institute.
The project emerged from the institute’s data study groups – a series of week-long events bringing together the disciplines of data science, analytics and mathematics to solve real-world problems.
At one of the groups, National Grid posed the challenge of how to improve the forecasting of intermittent renewable generation. After participants came up with a number of promising methods, the ESO decided the continue the work using funding from the Network Innovation Allowance.
Researchers utilised machine learning to generate hundreds of different algorithms that could correctly predict historical solar output based on around 80 different weather variables. These algorithms were then run using contemporary weather data and the results were averaged out to reach the new forecast.
By combining this “random forest” approach with other machine learning techniques, the ESO was able to improve the overall accuracy of its forecasts by a third (33 per cent).
It previously forecast solar generation on the basis of just two variables – installed solar capacity and solar irradiance.
“Renewable sources of power are becoming a bigger part of the energy mix so it’s vital our forecasts of their output are as accurate as possible,” said ESO commercial operations manager, Rob Rome.
“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.”
Andrew Duncan, data-centric engineering group leader at the Alan Turing Institute, added: “The project has opened up a lot of new avenues and ESO are interested in pushing other projects forward.
“There’s no shortage of problems to tackle.”
Please login or Register to leave a comment.