Method for short-term main-cause-hidden type prediction of power station photovoltaic power

Abstract

A method provided by the invention directs at the photovoltaic power of a designated power station, a power station photovoltaic power prediction model structure based on a simplified indirect causality radial basis function network is proposed, and a main meteorological factor ''solar radiation intensity'' that influences the power station photovoltaic power is reasonably hidden. Similar records are screened out from historical meteorology and photovoltaic power records according to a mahalanobis distance from a meteorological factor at a prediction time point, and a primary selection sample set with similar indirect influence factors is built, then a carefully selected sample set with similar indirect influence factors and results are selected according to a mahalanobis distance from the primary selection sample population, and then the carefully selected sample set is used to determine undetermined parameters in the prediction model structure, thereby realizing short-term power station photovoltaic power prediction modeling and prediction. The method not only simplifies a prediction model and is easy to realize prediction based on existing weather forecast information, but is also more accurate in principle, and the problem that existing power station photovoltaic power prediction methods are either not easy to realize or not accurate enough in principle is solved.

Description

technical field [0001] The invention belongs to the field of electric power engineering, and in particular relates to a main cause implicit prediction method of short-term power station photovoltaic power. Background technique [0002] At present, global photovoltaic power generation capacity is growing rapidly. Due to the inherent volatility and interstitiality, the adequacy of photovoltaic power generated by the power station to be absorbed by the power grid depends on the ease of implementation and accuracy of its prediction method. [0003] There are mainly two types of prediction methods based on direct or indirect causality in the existing PV power prediction methods of power stations. The prediction method based on direct causality needs to predict the solar radiation intensity on the ground first, and its complexity is the same as that of weather forecasting, which is not only difficult to implement but also low in accuracy. There are existing prediction methods ba...

AI Technical Summary

Problems solved by technology

The prediction method based on direct causality needs to predict the solar radiation intensity on the ground first, and its complexity is the same as that of weather forecasting, which is not only difficult to implement but also low in accuracy

There are existing prediction methods based on indirect causality, some of which require the solar radiation intensity of the upper boundary of the atmosphere or assume that the intensity is constant throughout the day, and complete the prediction of photovoltaic power at multiple points in a day through one mapping, which is not easy to realize or not accurate enough in principle (not yet It reflects the influence of the sun elevation angle from 0 to 0 in the morning, middle and evening, and then decreases to 0); some only consider the two influencing factors of temperature and humidity, and do not take into account the influence of important factors such as wind speed and cloud cover on heat dissipation and diffusion. reflection effect

In summary, the existing photovoltaic power prediction methods for power stations are either difficult to implement or not accurate enough in principle

Images