Image courtesy 123rf
A project run by Eaton and NREL has developed a tool that can detect powerline faults otherwise difficult to detect, enabling utility companies to reduce the chance of both power outages and wildfires.
The tool was developed by the power management company alongside the US’s National Renewable Energy Laboratory (NREL) via a project funded by the US Army Construction Engineering Research Laboratory (CERL).
Commenting in a release was Richard Bryce, a senior researcher in power systems at NREL and lead on the project: “The intention here is to enhance resilience in the power system and to enable faster responses during extreme events.
“We want to provide utility companies with the tools for a more resilient power system with better reliability and security for customers that mitigates the potential for wildfires caused by high-impedance faults.”
Have you read:
NREL geothermal storage project to tackle data centre grid stress
NREL-led lab to look into next gen power electronics
HiZ detection project
The project was designed to use machine learning to detect high-impedance (HiZ) faults, which is when an energised conductor, such as a fallen wire, comes into contact with the ground, causing a short. An HiZ fault produces a small amount of energy and are often not detected. But they can cause sparks that ignite flammable material in the area, which can ultimately lead to a wildfire.
For the project, Eaton conducted extensive evaluations in a simulated environment. The scenarios accounted for various downed-conductor events, such as different ground surfaces like grass and gravel, moisture levels, common US tree species, and other external considerations.
The resulting data was shared with NREL’s research team. Using NREL’s grid simulation capabilities and field data from multiple US utility companies, researchers were able to inject the data into the computer-aided design platform PSCAD (Power Systems Computer Aided Design). This then created a large dataset that included more HiZ fault scenarios than what could be produced in the field or in a controlled laboratory setting, says NREL in a release.
These simulated HiZ fault scenarios and datasets were used to train an ensemble of artificial neural networks (ANNs). These were down-selected to the most effective at identifying HiZ fault states, resulting in the tool, which NREL says is all but ready for real power systems. Once the ANN ensemble detects a fault, utility companies can prioritise sending resources quickly to that area to reduce the chance of both power outages and wildfires.
“There were pieces that came together beautifully for this project in a way that’s unique to NREL,” said Bryce.
“We had testing through our partnership with Eaton that provided real data that is experimentally derived, and then we were able to leverage NREL’s high-performance computing and machine learning to provide a solution to utilities which has a very significant, immediate real-world impact.”
NREL says their team is working with utilities across the country, as well as international partners, to generalise the technology, increasing the scalability of the algorithm to be broadly applicable in the US and beyond.
