UNSW and UTS Innovate Smart Sensing Solution for Solar Panel Performance – SolarQuarter

2 minutes, 31 seconds Read
Representational image. Credit: Canva

Australia’s solar energy sector is witnessing a transformation, thanks to a pioneering project aimed at addressing underperforming solar panels. The Smart Energy Asset Management Intelligence project, a collaboration between the University of New South Wales (UNSW) and the University of Technology Sydney (UTS), has developed innovative algorithms to diagnose and address issues in residential and commercial solar panels. These groundbreaking algorithms are scalable, automated, and cost-effective, offering a practical solution to a global problem.


Australia has one of the highest rates of rooftop solar deployment in the world, but underperforming panels have been a concern, leading to preventable losses. The Smart Energy Asset Management Intelligence project has found a way to tackle this issue, which is estimated to cost consumers around $US4.6 billion globally. The project’s innovative technology is already being used to monitor over 100 megawatts of solar assets, thanks to the integration into a commercial platform by industry partner Global Sustainable Energy Solutions.


Dr. Fiacre Rougieux from UNSW Sydney’s School of Photovoltaic and Renewable Energy Engineering, the Chief Investigator of the project, highlighted the game-changing nature of the algorithms, which can analyze inverter and maximum power point data every five minutes to diagnose underperforming issues. This timely diagnosis allows for early intervention and maximizes energy production.


The project developed a two-tiered approach to photovoltaic fault diagnosis. The first tier uses AC power data to detect broad issues such as zero generation and tripping. This approach is technology-agnostic and can work with any inverter and maximum power point tracker brand. The second tier, using both AC and DC data, provides more detailed insights, identifying specific faults like shading and string issues. This level of diagnosis combines statistical rule-based methods with machine learning for cases that defy conventional rule-based methods.

The project’s advancements have significant implications for energy production and system reliability. Dr. Ibrahim Ibrahim from UTS, who led the Institute of Sustainable Futures team, emphasized that the technology can significantly reduce preventable losses, resulting in substantial cost savings for photovoltaic system owners.

The NSW Smart Sensing Network Smart Cities Theme Leader, Peter Runcie, praised the project for its innovative use of sensors and analytical approaches to diagnose underperformance in commercial systems. The technology can pinpoint a wide range of issues, including wiring problems, degradation, and shading, as well as other challenges like clipping and tripping.

One remarkable aspect of the project is its ability to replace the need for expensive contractors on-site to diagnose underperforming systems. Dr. Rougieux noted that the algorithms could instantly detect issues that contractors might overlook for months. The project has also produced academic outputs, including conference papers and a literature review.

Moving forward, the team is working to enhance the algorithms to diagnose a broader range of issues, aiming to make a significant impact on the reliability of solar systems in Australia. With an expected 74GW of capacity online by 2035, even a small percentage of underperformance could result in billions of dollars in lost revenue, underscoring the importance of this innovation.

This post was originally published on 3rd party site mentioned in the title of this site

Similar Posts