A new fault detecting system is set to be rolled out at the Kidston solar farm in north west Queensland.
Solaris AI is a tech start-up from the University of Queensland (UQ) which uses machine learning algorithms to analyse data and detect faulty and underperforming solar panels.
In addition to Genex Power's farm at Kidston, discussions are also underway for the technology to be used at Edify Energy's Hamilton solar farms at Collinsville.
The system is the work of UQ associate professor Rahul Sharma.
"The challenge with large solar farms is detecting any faulty or underperforming solar panels hidden in a sea of millions," he said.
Solaris AI is an all-in-one solar farm operation and maintenance system
- Dr Rahul Sharma
"It's impractical to install monitoring hardware on each panel, inspect every panel for damage or clean every panel to remove dirt.
"We needed to find a way to automate that process."
Dr Sharma said underperformance in Australian solar farms cost the industry about $400 million a year and Solaris AI is aiming to reduce those losses by half.
The technology works at the array and string panel level - the system connecting multiple panels together.
The AI then sequentially extracts information, monitoring for degradation, soiling, wiring faults and tracker problems, along with pinpointing any maintenance needed.
The system works with data already available at the solar farms, not requiring any specific hardware installations to work.
Dr Sharma said the Solaris AI technology has been tested in an experimental setup. This was followed by a pilot study on a small scale solar farm and then trialled on an Australian commercial solar farm.
He said if appropriately used, there is potential to deliver a revenue uplift of eight per cent per annum.
"Solaris AI is an all-in-one solar farm operation and maintenance system," Dr Sharma said.
"It is meant to detect, locate, identify any faults and underperformance issues in large solar farms. It also tries to see if there are any trends or patterns which indicate likelihood of occurrence of the faults in the future.
"That way we can schedule preventive maintenance work prior to the occurrence of the faults so that any major disruptions can be avoided."
Edify Energy CEO John Cole said it was an exciting project.
"The key to maintaining grid reliability and achieving success as a network operator is effective and efficient asset management," he said.
"This technology has the potential to drive solutions to the world's energy crisis."
The project partnered with German-based electronics and connection technology company Weidmueller to develop early prototypes.
SolarisAI was founded by UQ's commercialisation company UniQuest, spearheaded by investment from Uniseed as well as the UniQuest Investment Fund.
UniQuest CEO Dr Dean Moss said it was an exciting time for the UQ start-up, with Australia's solar generation capacity on the cusp of stellar growth.
"UQ is committed to sustainable energy and renewable energy generation," he said. "This is a fantastic commercial opportunity backed by top-notch research with the potential to generate huge economic and environmental benefits."
Dr Sharma said it is a dream to see his research transition to the real world.
"I think the ultimate satisfaction will be if this technology delivers benefits to the solar farm owners and operators," he said.
