METHODS AND SOFTWARE TOOL FOR AUTOMATING STATIC AND DYNAMIC SEARCH FOR ANOMALIES IN TELEMETRY DATA OF A SOLAR POWER PLANT

Annotation: The search for faulty, and therefore operating in an abnormal mode, solar panels at a power plant is an urgent task in the context of the development and growth of the share of solar energy in electricity generation. The purpose of the study is to develop new methods and software algorithms for finding anomalies in the operation of solar panels based on the results of a digital twin created and trained according to the telemetry data of a solar power plant. Methods: The developed methods are based on studies of deviations of power values at the point of maximum efficient operation of the solar panel calculated by a digital twin from the average statistical values for the power plant. In addition, the normalized power value at the point of maximum efficient operation of the solar panel is introduced. Results. Using the developed methods of static search for half a year of observations, 18 anomalies in the operation of the solar panels of the power plant were detected and confirmed using direct Observation: 16 using the static analysis method and 2 using the dynamic analysis method. Conclusions: It has been established that when using normalized power values in MPP PN in the analysis of deviations, it is possible to detect anomalies in the operation of solar panels.