Thingnario, a Taiwan-based solar PV monitoring service provider that uses AI to interpret large data sets, reported that large solar farms can save up to $4,000 per megawatt in avoidable losses each year. The data comes from more than 3,200 photovoltaic sites in Taiwan, studied over four years. Thignario believes that higher quality O&M monitoring can recoup much of these costs through its proven strategies.
Thingnario’s report, titled “Taiwan PV Performance Report”, presents its information courtesy of more than 100,000 IoT devices, including inverters, power meters, pyranometers, weather stations, etc., and covering 45% of the new installation market in Taiwan. The total data weight totals more than 273 terabytes.
While the report focuses on loss avoidance, other interesting data nuggets emerge: Although Taiwan only covers 394 km from north to south, southern Taiwan has most of the island’s solar power plants for avoid more persistent clouds and rain in the north.
The report focuses more on recoverable energy losses, which average 2.16% of all energy generated per plant. Thignario shows that at least a third of losses can be corrected through monitoring and timely and appropriate O&M.
The report also examines avoidable and recoverable losses and quantifies them. The identification of avoidable losses comes from the separation of recoverable and irrecoverable losses, the latter not being taken into account in the report. These losses are considered irreversible and relate to module losses and orientation, ohmic losses in the wiring, inverter conversion losses, etc.
Recoverable losses are discussed in more detail. These losses are then distributed between availability, that is to say complete losses due to failures or complete failures of equipment, and performance losses. Performance losses are due to equipment efficiencies and inefficiencies, where peak efficiency is maintained through better maintenance and control. An example is if a fan on an inverter fails or the inverter overheats. This is recorded as a loss in performance, since these losses can be corrected by proper management, namely quality control and proper maintenance.
Thignario’s data indicates better results for solar parks with proper operation and maintenance. The report suggests that performance losses, in particular, can be minimized through monitoring systems that combine with data analytics, providing both accurate and instantaneous notifications, followed by prompt action by security teams. qualified maintenance.
The company suggests that using its own AI monitoring system combined with a well-trained and responsive O&M team saves $4,200 per 1 MW. This figure comes from data suggesting that the average downtime for equipment repair is 123.6 hours. However, a better O&M team can reduce that downtime to 52.1 hours. In turn, this helps reduce recoverable losses to just 2.16% of all energy generated.
Per megawatt, losses average 29,3768 kWh, but better O&M performance can reduce this average to 8,475 kWh, a savings of 70%.
The general availability of PV plants can be analyzed by monitoring inverter, MPPT and string downtimes. However, the exact performance losses remain complicated to gauge, with production data unable to tell the full story. Thignario’s approach is to use AI to understand how much electricity is wasted and where improvements can be made, by learning patterns and comparing real-time performance and real-time environmental changes.
Thignario has developed deep learning algorithms that discover different types of on-site and sometimes hidden anomalies. The system can calculate the possible loss and immediately notify the O&M team of the issues. The process is further enhanced by the learning system that collects quick feedback from the O&M team, creating an iterative system that allows the algorithm to upgrade and evolve. In turn, this provides an accurate and comprehensive analysis of abnormal performance and issues.
FIT causes flow
Taiwan’s high feed-in tariff (FIT) rate has previously insulated domestic PV sites from significant losses due to poorer operation and maintenance practices. Feed-in tariffs started at $0.35 per kWh for small-scale rooftop solar installations and $0.25 for large-scale ground-mounted solar installations. However, with lower feed-in tariffs now taking over, priced at around $0.14 per kWh, PV site monitoring is now much more important, and monitoring is the first step towards actionable management, through correct and transparent information.
William Kao, COO of thingnario, noted that the transition was catching up with some photovoltaic investors. “The energy revolution is underway,” he said. “Paying attention to how to use every piece of renewable energy equipment we invest in is critical in this pivotal year.”
The steps taken in Taiwan to reduce feed-in tariffs follow similar situations in Australia, the United Kingdom and Germany, which reduced PV tariffs on a large scale in 2011 following a drastic reduction in costs. PV installations and have caused changes in operational approaches.
This content is copyrighted and may not be reused. If you wish to cooperate with us and wish to reuse some of our content, please contact: [email protected]