Researchers in China have developed a dust monitoring technique that relies solely on existing inverter hardware resources, without the need for additional sensors or meteorological data. Tests on real rooftop PV arrays have shown accuracy of over 96%.”
Researchers in China have developed a new localized dust accumulation monitoring technique for distributed photovoltaic arrays that relies solely on existing inverter hardware, eliminating the need for additional devices or internet connectivity.
“For distributed PV systems with relatively modest energy generation revenues, dependence on additional devices or external services will inevitably increase the initial investment and extend payback times,” the team explains. “Additionally, these methods often involve complex procedures that are difficult for non-specialists to implement. To address the need for cost-effective and practical dust monitoring, this study proposes a localized monitoring approach.”
The new method utilizes the operation of multiple panels within the same local area, allowing the system to consistently identify dust accumulations based on operational data. In this setup, inverters collect and screen relevant data, which is then compressed using an enhanced differential coding (DE) scheme applied to voltage, current and their duration.
A gated recurrent unit (GRU) artificial intelligence model then extracts features and identifies patterns, while a semi-supervised K-means algorithm groups data into clean and dirty clusters using labeled examples. Daily results are statistically aggregated and when consistent patterns emerge, the system issues an alert. Data collected before and after each cleanup operation is treated as newly labeled instances, updating the sample set for future monitoring.
To evaluate the system, the researchers tested three groups of PV arrays: Group 1 with 230 W polycrystalline silicon panels, seven years of service, 1×13 topology and a total power of 2.9 kW; Group 2 with 275 W polycrystalline silicon panels, eight years of service, 2×9 topology and a total power of 4.9 kW; and Group 3 with 135 W monocrystalline silicon panels, two years of service, 2×6 topology and a total power of 1.6 kW.
All inverters were three-phase full-bridge types with a rated power of 10 kW. Data was collected over 12 days under sunny, cloudy and cloudy conditions, with each PV group tested under four different dust coverage scenarios, simulated using plastic films with transmission rates of 85%, 72% and 61%. Of the 302,400 data points collected, 4,139 were retained after screening, with 3,139 used for training and 1,000 reserved for testing.
The system showed an accuracy of 96.5%, slightly lower than the 98% accuracy of reference cloud-edge collaboration approaches.
“The proposed approach ensures low cost, low operational complexity and high accuracy in dust accumulation monitoring, reducing maintenance and management costs for distributed PV systems and improving owner profitability,” the team concluded.
The new approach was described in “Localized dust accumulation monitoring for distributed photovoltaic arrays”, published in Solar energy. The research team included scientists from China’s Shandong University of Science and Technology and Shandong University.
This content is copyrighted and may not be reused. If you would like to collaborate with us and reuse some of our content, please contact: editors@pv-magazine.com.
