Operations and maintenance personnel no longer need to conduct onsite inspections of entire PV plants. In 2019, Huawei launched its AI Boost Smart I-V Curve Diagnosis 3.0. By scanning PV strings using its smart PV inverters, the solution can find the relationship (I-V curve) between output voltage and output current. Huawei says the smart PV management system uses big data to analyze the I-V curve of PV modules, applies artificial intelligence (AI) diagnosis algorithms, identifies faulty strings, and creates a diagnosis report.
“Thanks to AI self-learning, the solution continuously accumulates I-V experience and optimizes fault models, marking the start of AI operations and maintenance for PV,” says Yan Zhang, senior product manager of Huawei.
“Faults in solar PV modules affect a plant’s energy yield more than any other factor. These faults vary greatly depending on the stage at which they occur,” says Zhang. He argues that manual inspection and traditional supervisory control and data acquisition (SCADA) often cannot pinpoint the root cause of faults with accuracy in a short period of time.
Traditionally, an I-V inspection has required personnel to visit project sites, bringing equipment with them. A 100 MW PV plant has tens of thousands of PV modules and covers an area equivalent to more than 300 football fields. “Physically scanning all PV modules is just not practical,” says Zhang, adding that manually generated reports can result in errors and is also time-consuming. Increasing application scenarios, challenging terrain, and the advent of new types of solar PV modules. such as bifacial technology, can make for particularly complex and expensive manual inspections.
Huawei’s Smart I-V Curve Diagnosis 3.0 offers an alternative to the manual sampling method of detection. The system is said to perform full detection on all PV modules and automatically generates detection reports covering 14 different types of faults, accompanied by automated reports. “The AI Boost Smart I-V Curve Diagnosis supports remote scanning of all PV strings in one-click mode,” says Zhang, claiming that a 100 MW PV plant can be scanned within 15 minutes.
More from our partners
As the detection is completed online, it negates the need for site visits. “This greatly improves the O&M efficiency of PV plants by more than 50% and reduces O&M costs over the lifetime of the system,” says Zhang.
The AI technologies further collect expert experience to search, filter, check, and identify faults – proactively maintaining the health of PV plants for long periods. In this context, maintenance does not refer to locating specific faults. Instead, it refers to comparing performance indicators and the data provided by sensors with algorithms to check whether solar PV plant devices are running properly. Once an exception is detected, a warning is generated.
Huawei says its solar PV solution works similarly to the fault preprocessing systems that have already been widely adopted in the field of aviation. For example, when an aircraft engine is about to fail, a warning will be first delivered to the airline control center. Subsequently, the control center will provide the pilot with instructions, and arrange maintenance personnel to arrive at the destination in advance to eliminate potential risks before an accident occurs.
The Smart I-V Curve diagnosis solution from Huawei is said to have already been utilized for various PV plant setups, for residential rooftops, commercial & industrial, and utility-scale groundmount applications. “We are currently the only vendor that have successfully applied Smart I-V Curve Diagnosis on a large scale,” says Zhang, referencing a 100 MW smart PV plant in Golmud, in China’s Qinghai province, where he says Huawei’s Smart I-V Curve Diagnosis detected all strings within 15 minutes. “It accurately detected and identified all faults, supporting our customer to increase their revenues by CNY 10 million ($1.39 million).”
For a 50 MW solar PV plant in the mountains of Datong, in China’s Shanxi province, Huawei says its Smart I-V Curve Diagnosis was used to scan 14,626 PV strings. It detected 909 faulty strings, with a fault rate of 6.21%. Based on the Smart I-V Curve Diagnosis report, O&M personnel gained a detailed understanding of the condition of each PV array, which allowed them to take a more targeted approach to site maintenance. Zhang says, “The resulting impacts are estimated to save them CNY5.42 million in maintenance costs over 20 years.”
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: firstname.lastname@example.org.