Outlier data mining method considering the output distribution characteristics for photovoltaic arrays and its application

Abstract

Sustainable growth of the installed capacity for photovoltaic (PV) power has brought greater challenges to the operation and maintenance of PV plants. As important functions of smart operation, the performance analysis, modeling, evaluation and fault diagnosis, are getting more demanding. However, large amount of outliers are generated during the running of the PV arrays in the plant, which brings many difficulties for the implement of above functions. To solve this problem, an outlier cleaning method considering the output distribution characteristics for PV arrays is proposed. First, the distribution characteristics of PV array operation data under different external environmental conditions are analyzed, and the distribution characteristics and laws of outliers are discussed. Next, based on the array output characteristics, a two-step quantile algorithm is used to modify the outliers. Subsequently, a case study shows that the proposed method can effectively identify different types of outliers. The main contributions of the paper are the explanation of the PV array outliers distribution affected by the external environment, and the first application of the data cleaning method to the thresholds setting of PV arrays operating and its fault diagnosis.

Keywords

• PV power
• Output distribution
• Outlier cleaning
• Fault diagnosis
• Quantile algorithm