Skip to main content
News Networks

National Grid ESO eyes dynamic day-ahead reserve setting in Smith Institute project

Machine learning algorithms are to be developed as part of the project to more accurately predict reserve requirements. Image: National Grid.

Machine learning algorithms are to be developed as part of the project to more accurately predict reserve requirements. Image: National Grid.

National Grid ESO is to explore moving to dynamic day-ahead reserve setting as part of a new project with Smith Institute.

The ESO is aiming to adopt a new, fully dynamic day-ahead approach to scheduling reserve, which is the back-up power it keeps in readiness in case it’s needed. This would boost the efficiency of balancing actions and improve value for consumers, it said.

As it stands, the ESO sets reserve levels that vary according to electricity demand seen at different times of the day and the week, with levels informed by historical generation and forecasting errors and adjusted by forecast renewable generation output.

However, these could potentially be optimised to take better account of the effect of forecast weather conditions in the system by linking generation and forecasting errors to weather driven effects or other variables, and buying reserve in day-ahead timescales.

As such, the Smith Institute is to develop a proof-of-concept machine learning model. This will use predictor variables such as temperature and wind forecast data to create more accurate predictions of forecast errors to account for the variability in weather on a day-to-day basis.

The model will help the ESO better understand where there are uncertainties in its forecasting data as well as set reserve levels more accurately, with this then potentially limiting the need to keep fossil fuel plants running as back-ups.

If the proof-of-concept is successful, the algorithm will be integrated into the ESO’s systems for a live trial. The initial proof-of-concept is expected in November 2021, with the project set to last for around twelve months.

Isabelle Haigh, head of national control for National Grid ESO, said: “As more clean energy connects to Britain’s electricity system, the network is becoming more challenging to operate.

"The more confidence and certainty we have in our forecasts, the more efficiently and securely we’ll be able to balance the country’s supply and demand day to day, minute by minute."

The project - which is funded through the Network Innovation Allowance (NIA) - forms part of National Grid ESO's innovation portfolio.

Other projects within the portfolio include Distributed ReStart, looking at how distributed energy resources (DER) can be used to restore power in the event of a total or partial shutdown of the electricity transmission system, and Power Potential, which is aiming to create a reactive power market for DERs.

In March, National Grid ESO published its Innovation Strategy, making digital transformation its top priority for the year as future markets and constraint management took second and third spots respectively.


End of content

No more pages to load