Cloud cluster movement estimation method facing to photovoltaic power prediction

Abstract

The invention provides a cloud cluster movement estimation method facing to photovoltaic power prediction. The cloud cluster movement estimation method for the photovoltaic power prediction comprises the following steps: preprocessing an image of a ground-based cloud picture; thresholding the ground-based cloud picture; detecting and marking a cloud cluster and extracting center of mass of the cloud cluster; and estimating moving speed and direction of the cloud cluster. By the cloud cluster movement estimation method for the photovoltaic power prediction, each cluster in a time sequence image is tracked and studied to determine the moving speed and direction of the cloud cluster in the future, so that the cloud cluster movement in the future is estimated, and an important data source is provided for minute-grade power prediction within a super-short period of 0-4 hours for a photovoltaic power station.

Description

technical field The invention belongs to the technical field of photovoltaic power prediction, and in particular relates to a cloud movement prediction method for photovoltaic power prediction. Background technique In recent years, large-scale photovoltaic power plants have been connected to the power grid. Due to the randomness and volatility of the output power of photovoltaic power generation, it has affected the safety, stability and economic operation of the power grid. Accurately predict the output power of photovoltaic power plants, provide important decision support for power dispatching, coordinate the coordination of conventional power and photovoltaic power generation, reduce power system operating costs, and help make full use of photovoltaic resources to obtain greater economic benefits and social benefits. Ground irradiance is one of the main factors affecting the output power of photovoltaic power plants, and its uncertainty directly leads to the randomness...

AI Technical Summary

Problems solved by technology

Some foreign scholars predict the solar irradiance based on meteorological satellite cloud images to estimate cloud movement, but its temporal and spatial resolution is relatively low. Cloud image data with Earth-height spatio-temporal resolution

Images