Research on the method of constructing a photovoltaic characterization model based on big data driving

With the growing global demand for clean energy, the photovoltaic (PV) industry is rapidly emerging as a key force in driving the energy revolution and realizing the green transformation of the economy, as it accounts for an increasing proportion of the energy mix. Among them, PV characterization models are crucial for understanding and optimizing PV system performance. However, traditional models have limitations in terms of data volume, generalization capability, and parameter accuracy. Therefore, in this paper, the Spearman correlation coefficient method is firstly used to identify the key factors affecting the efficiency of PV equipment and then combined with multifactor Analysis of Variance (ANOVA) and elastic network regression methods. The correlation between key factors such as PV module surface temperature, inverter load factor, solar panel DC current and voltage, and PV equipment efficiency is investigated through the arithmetic analysis. The results show that there is a significant correlation between these factors and PV equipment efficiency and that the effects of these factors on PV equipment efficiency can be effectively assessed by the combined multifactor ANOVA-elastic network regression method.