基于气象相似性的光伏电站输出功率估计

In order to obtain the output power of photovoltaic power plants, an output power estimation method based on meteorological similarity is proposed. This method analyzes a large number of historical data, using the characteristics of photovoltaic power plant output power and meteorological data are closely related, based on the Pearson correlation coefficient to calculate the similar meteorological time to the estimated output power in the historical data. Finally, according to the similar meteorological time's output power estimates the output power at the time to be estimated. The used historical data contain 9 meteorological elements from a photovoltaic power station in Gansu Province. After data preprocessing, a 214-day data set containing no abnormal data are selected as the data sample, in which 14-day data of different weather types are randomly selected as the test samples, and the rest are used as training samples. Case study indicate that the average absolute error and relative error of the proposed estimation method are only 0.46 MW and 15.74%, respectively. It has high calculation accuracy and is applicable to a wider range of meteorological conditions.