Cloud Displacement Vector Calculation in Satellite Images Based on Cloud Pixel Spatial Aggregation and Edge Matching for PV Power Forecasting

Cloud movement is the main factor affecting photovoltaic (PV) power fluctuations. This paper aims to calculate the displacement vector of clouds in satellite images. Due to the large amount of data and the deformation degree of clouds, the existing cloud displacement vector algorithms have poor speed and accuracy when processing satellite cloud images. Therefore, this paper proposes a cloud displacement vector calculation method in satellite images based on cloud pixel spatial aggregation and edge matching, which can improve the accuracy and speed. The algorithm also obtains the movement information of different positions of clouds and the trend of cloud extinction and deformation can be analyzed. The test was performed using data from FY-4 satellite images of China. The results show that the cloud displacement vector algorithm designed in this paper has been greatly improved in calculation speed and accuracy, and the calculation error is less than 10%.