Sensing a solar revolution for underperforming panels

Australia may proudly boast it has the highest per capita deployment of rooftop solar in the world, but underperforming panels are costing consumers.

Now an NSW Smart Sensing Network Grand Challenge project has found a way to tackle the blight of solar panel underperformance, which is costing an estimated $US4.6 billion globally in preventable losses.

The Smart Energy Asset Management Intelligence project has created game changing multi-stage algorithms which can remotely detect why many residential and commercial solar panels and other renewable energy systems are underperforming.

The algorithms are practical in that they are scalable, automated, and cost-effective.

The algorithms could replace the need for expensive contractors on site to find out why a solar system is underperforming. Credit: AdobeStock.

The project is a collaboration that has involved researchers from UNSW and the UTS Institute of Sustainable Futures, as well as industry partners Global Sustainable Energy Solutions and the Australian Photovoltaic Institute.
Government partners - including Lake Macquarie City Council, Lachlan Shire Council, City of Newcastle Council, Canada Bay Council and Bathurst Regional Council – were approached for their data to create the algorithms for the software.

Dr Fiacre Rougieux from UNSW Sydney’s School of Photovoltaic and Renewable Energy Engineering is the Chief Investigator of the Smart Energy Asset Management Intelligence project.

He said the algorithms have revolutionised the monitoring of photovoltaic systems.

“By analysing inverter and maximum power point data every five minutes, this algorithm can accurately diagnose underperforming issues, enabling early intervention and maximising energy production,” Dr Rougieux said.

The innovative technology developed in the project has now been fully integrated into a commercial production platform, which is being used by one of the project’s industry partners Global Sustainable Energy Solutions to monitor more than 100 megawatts of solar assets.

Dr Rougieux said the project had developed a two-tiered approach to photovoltaic fault diagnosis.

“We have created a high-level diagnosis using just AC power data, which can detect broad categories of issues such as zero generation and tripping,” he said. “The benefit of this approach is that this diagnosis is fully technology agnostic and can work with any inverter and maximum power point tracker brand.

“As many inverter brands give rich AC and DC information, we have also developed a more detailed algorithm using both AC and DC data, which can provide more actionable insights for asset owners by detecting and classifying more specific faults like shading and string issues.

“This type of diagnosis requires both statistical rule-based methods backed up by machine learning approaches for cases which cannot be captured by conventional rule-based methods.”

Leader of the UTS Institute of Sustainable Futures team, Dr Ibrahim Ibrahim, said the advancements have enabled proactive measures that maximise energy production and enhance system reliability.

“By significantly reducing preventable losses—which are valued in the billions globally—such technologies ensure substantial cost savings for photovoltaic system owners,” Dr Ibrahim said.

(From L to R) Dr Fiacre Rougieux, Dr Ibrahim Ibrahim and Peter Runcie.

NSW Smart Sensing Network Smart Cities Theme Leader Peter Runcie said NSW has long been a pioneer in renewable energy innovation. 

“The project focused not so much on the solar cells themselves, but on how the photovoltaic system as a whole is operating,” Mr Runcie said. 

“It used sensors and different types of analytical approaches to automatically detect and diagnose underperformance of commercial systems. 

“Here we have an excellent example of a smart sensing research project involving a collaboration between UNSW, UTS, industry partners and local governments.”

Diverse algorithms

The diverse algorithms can be implemented on more than 1200 photovoltaic systems.

The technology can pinpoint a wide range of common solar panel issues such as wiring issues, degradation, and shading from trees, as well as:

Clipping – when a system produces more PV power than can be exported to the grid resulting in clipping and lost power.

Tripping – occurs in the inverter when there is too much solar in the grid.

Export limit – this is reached usually on weekends when there is no consumption of power.

Dr Rougieux said the software could replace the need for expensive contractors to go on site to find out why a solar system is underperforming.

“We had a council which had an underperforming system for five months straight,” he said.

“That contractor had an Operation and Maintenance contract in place, yet this major issue remained undetected for months. Our algorithms picked it up almost instantly.

“The big surprise for us was the staggering number of systems where an operations and maintenance contractor completely missed the underperformance that we detected.

“The problem is that there’s not one person that has the expertise to understand why their systems are not working to peak performance.”

Next steps

The team are now working on enhancing the algorithm so that it can diagnose a broader range of issues such as shading, soiling and detailed grid side faults.

The project has resulted in two conference papers and a literature review paper which is under review.

“This is a game changer for Australian residential and commercial system operators,” Dr Rougieux said.

“By 2035, 74GW of capacity is expected to be online according to the AEMO Integrated System Plan. But if there is 10 per cent underperformance, that could mean more than a $1billion being lost in Australia alone. Everyone is currently focusing on efficiencies, but we need to focus on reliability.”

Diane Nazaroff