SP Energy Networks is trialling the use of artificial intelligence (AI) to better pinpoint potential faults on the electricity network caused by severe weather and help ensure equipment and engineers are on hand to tackle problems.
The £5 million Predict4Resilience project will use AI to predict where faults could occur up-to seven days in advance. Historic weather and fault data are combined with network asset and landscape information to develop machine learning models. Combined with real-time weather forecasting, Predict4Resilience will inform SP Energy Networks’ control room about where the weather will hit and what damage is expected.
Guy Jefferson, Chief Operating Officer at SP Energy Networks, said: “Ahead of a severe weather event we mobilise hundreds of engineers, vehicles, and generators alongside thousands of pieces of other materials so we are ready to restore power as quickly and as safely as possible…
“Projects like Predict4Resilience offer us another tool to help inform our decision making during a storm and help to reduce the time it takes us to restore power, minimising the impact of severe weather on our customers and communities even further.
The network is working with the University of Glasgow, which is developing the AI that underpins forecasting and Sia Partners, a global consultancy with the technical capabilities to build the software and its supporting infrastructure. Scottish and Southern Electricity Networks Distribution will test the findings in its area, resulting in a wider scale area being tested. Sia Partners will use its business expertise to ensure the technology can be rolled out across all network operators
The project secured £4.5million funding from the Strategic Innovation Fund (SIF) from energy regulator Ofgem and UK Research and Innovation (UKRI).