Western Power Distribution to use AI for flexibility services forecasting

A more accurate forecasting tool will facilitate the UK's transition from a DNO to DSO model.
Published: Wed 11 Sep 2019

As part of its Electricity Flexibility and Forecasting Systems (EFFS) project, Western Power Distribution (WPD) used techniques designed by Smarter Grid Solutions (SGS) to improve the accuracy of the forecasts needed to run flexibility services. WPD is the distribution network operator (DNO) for the Midlands, South West England and South Wales.

The need and value of flexibility services depend on their location and speed of response but also the demand and generation on the network close to real-time, which can be difficult to predict. SGS uses two techniques known as “long short-term memory” (LSTM) and “extreme gradient boosting” (XGBoost) to make predictions, which it says are more effective than “auto-regressive integrated moving average”, the current most commonly used load forecasting tool, and techniques used in recent network innovation projects.

Other DNOs are considering if they can use the technology, says SGS, including Scottish Power Energy Network for its FUSION project and Scottish and Southern Electricity Network for TRANSITION project, which are also looking at forecasting methods. 

SGS’s project used open-source tools so the results are freely available to use without licence.

SGS’s work delivered forecasts for 132kV and 33kV networks for grid supply points, bulk supply points, primary substations, large load customers and renewable generation. Timeframes from six months ahead down to one-hour ahead were examined.


These kind of technologies will assist DNOs as they transition to system operators which more responsibility for balancing the network, according to SGS. Dr Graham Ault, executive director and co-founder of SGS, said: “The results from our forecasting models were very good, especially for the shorter timeframes. The accuracy levels achieved outperformed known forecasting methods used on other recent innovation projects, so these results are really pushing the industry forward. 

“XGBoost performed very well and outperformed the other methods in most test cases and applications.

“This is an exciting time for the electricity industry, with network operators making the transition from DNOs in the conventional network operator model to playing a more active management role as Distribution System Operators (DSOs).”

Jenny Woodruff, EFFS project manager at Western Power Distribution, added: “It’s exciting for us to be working with an innovative company like SGS on our transition from a DNO to a more advanced DSO.

 “Being able to accurately forecast demand and generation will enable us to identify where and when our network will need flexibility services.  The more accurate the forecasting, the more efficiently we can purchase and dispatch these services.  We’re looking forward to scaling up the method used by SGS to create forecasts for a larger number of sites to support the EFFS trial. 

“Using flexibility services effectively will become ever more important as our heating systems switch from gas to electricity and as increasing numbers of businesses and households swap to electric vehicles.”

SGS’s Forecasting Evaluation Report is available from the WPD Website at https://www.westernpower.co.uk/downloads/43210

SGS recently announced that it is expanding into Europe after successfully demonstrating “dynamic curtailment” at a German utility, where very small amounts of electricity produced by renewable energy generators like wind farms or solar parks is reduced if too much power is pumped into the grid. 

This will reduce the amount of curtailment required by existing dispatch methods.