Practical recommendations for the design of automatic fault detection algorithms based on experiments with field monitoring data. (15th September 2022)

• Record Type: Journal Article
• Authors: Sarquis Filho, Eduardo Abdon; Müller, Björn; Holland, Nicolas; Reise, Christian; Kiefer, Klaus; Kollosch, Bernd; Branco, Paulo J. Costa
• Is Part Of: Solar energy. Volume 244(2022)
• Page Start: 227
• Page End: 241
• Publication Date: 2022-09-15
• Subjects: PV system -- System performance -- Operation & maintenance -- Defects -- Automatic detection; Solar energy -- Periodicals; Solar engines -- Periodicals; 621.47
• DOI: 10.1016/j.solener.2022.08.022
• Languages: English
• ISSNs: 0038-092X

Abstract

Abstract: Automatic fault detection (AFD) is a key technology to optimize the Operation and Maintenance of photovoltaic (PV) systems portfolios. A very common approach to detect faults in PV systems is based on the comparison between measured and simulated performance. Although this approach has been explored by many authors, due to the lack a common basis for evaluating their performance, it is still unclear what are the influencing aspects in the design of AFD algorithms. In this study, a series of AFD algorithms have been tested under real operating conditions, using monitoring data collected over 58 months on 80 rooftop-type PV systems installed in Germany. The results shown that this type of AFD algorithm have the potential to detect up to 82.8% of the energy losses with specificity above 90%. In general, the higher the simulation accuracy, the higher the specificity. The use of less accurate simulations can increase sensitivity at the cost of decreasing specificity. Analyzing the measurements individually makes the algorithm less sensitive to the simulation accuracy. The use of machine learning clustering algorithm for the statistical analysis showed exceptional ability to prevent false alerts, even in cases where the modeling accuracy is not high. If a slightly higher level of false alerts can be tolerated, the analysis of daily PR using a Shewhart chart provides the high sensitivity with an exceptionally simple solution with no need for more complex algorithms for modeling or clustering. Highlights: Recommendations for designing automatic fault detection algorithms for PV systems. Results based on tests with 5 years monitoring data from 80 rooftop-type PV systems. Statistical analysis based on clustering shows very few false alerts in all cases. Using less accurate modeling increases sensitivity, but decreases specificity. Daily PR monitoring with control chart can be a reasonable and simple solution.