Researchers developed a new method to measure solar panel degradation, according to a report published on January 10, 2019.
The newly developed method will be useful in inspecting the performance level of cells, as over time, solar cells get damaged due to weather, temperature changes, soiling, and UV exposure. Over the past few years, Parveen Bhola, a research scholar at India’s Thapar Institute of Engineering and Technology and Saurabh Bhardwaj, an associate professor at the same institution have been working on developing and improving statistical and machine learning-based alternatives to enable real-time inspection of solar panels. Through their research, a new application for clustering-based computation was found and it used past meteorological data for computing performance ratios and degradation rates. This method also allows for off-site inspection.
Clustering-based computation is a better option for this problem due to its ability to carry out the inspection rapidly, thereby preventing further damages and hastening repairs. This is done by using a performance ratio based on meteorological parameters that include temperature, pressure, wind speed, humidity, sunshine hours, solar power, and even the day of the year. The parameters are easily acquired and assessed, and can be measured from remote locations.
Inspectors would be able to troubleshoot more efficiently if the PV cell inspection systems are improved. Moreover, they could potentially forecast and control for future difficulties. Clustering-based computation will be useful in optimizing PV yields, thereby inspiring future technological advancements in the field.
Researchers say that majority of the available techniques calculate the degradation of PV (photovoltaic) systems by physical inspection on site, which is a time-consuming and costly process. Therefore, these techniques are not preferred. The benefits of real-time PV inspection go beyond time-sensitive and cost-efficient measures. Bhola said, “As a result of real-time estimation, the preventative action can be taken instantly if the output is not per the expected value. This information is helpful to fine-tune the solar power forecasting models. So, the output power can be forecasted with increased accuracy.”