Storm Resilience is developing new software to reduce the number and length of power cuts during a storm. The project could help restore power supplies caused by lightning strikes up to 90% faster, and ensure we have engineers in the right places to reduce the time taken to repair faults caused by a storm.
UK Power Networks’ ‘Storm Resilience’ project will use a machine learning algorithm to help control room staff decide where to send engineers, so they are ready to respond as storms occur. A separate part of the project will trial lightning tracking software that could help restore power supplies caused by lightning strikes up to 90% faster.
This project supports the drive to be an even more reliable network operator through improving the resilience during severe events. It is split across two separate initiatives;
We are trialling a proof of concept where UK Power Networks’ Network Management System (PowerOn) will receive lightning strikes locations in real time via an API developed by an international weather consultancy. These locations will be linked to poles and to the network diagram. After this mapping is established, a dedicated alarm will be created in PowerOn to notify control engineers that the faulted circuit was likely struck by lightning. This could reduce the time customers are off supply due to lightning strikes.
We will gain access to advanced weather forecasting from stations across the UK Power Networks licence areas. This work stream will trial the concept of using predictive analytics to combine historic fault data to weather parameters. This will build on and enhance our existing capabilities to forecast the impact of severe weather. The novelty will be within the development of the link between high frequency sampled weather data and the distribution network. This will ultimately drive a numerical prediction of weather related fault volumes and locations. These forecasts will provide a probabilistic view of the storm impact and quantify the expected level of risk each weather event presents.
Lightning into PowerOn aims to input real-time lightning data into our network management system, and identify when a fault is caused by lightning. Using lightning data to this accuracy has never been trialled before. If this proof of concept is successful, the next stage will integrate this functionality into our automatic power restoration system, enabling us to restore a power cut due to lightning in less than 3 minutes.
The Resource Estimation Tool aims to combine network data, historic fault data, and advanced weather forecasts to predict the number of faults each region will experience during bad weather. This will drive a ‘probabilistic fault forecast’, which has never been trialled for a UK electricity network. The tool will automatically tell us where and when to allocate resources and staff hours far more accurately than humans are capable of. Machine learning will then be used to help improve the tool overtime.
We will trial the new technology throughout 2021 in order to capture sufficient lightning activity and prove the concept on the live system. The trial will identify if the accuracy of the lightning data is sufficient and will assess how it integrates with our present automatic restoration systems.
We will trial the tool from August to prove it is capable of forecasting, planning and responding to severe weather events effectively. During the trial we will measure how well it can optimise the number and location of resources during a weather event and how it compares to our present processes. We also hope to identify additional data sources that may help improve the tool in future development.