New energy power prediction method based on improved wavelet transform and neural network
The invention relates to a new energy power prediction method based on improved wavelet transform and a neural network. The method comprises the steps of obtaining multiple groups of meteorological data samples and historical generated power, determining relevancy between a meteorological numerical...
Saved in:
Main Authors | , , , , , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
08.07.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention relates to a new energy power prediction method based on improved wavelet transform and a neural network. The method comprises the steps of obtaining multiple groups of meteorological data samples and historical generated power, determining relevancy between a meteorological numerical value sample under each variable type and the historical generated power, obtaining an initial variable type corresponding to each relevancy threshold value, and according to first training precision corresponding to the initial variable type, obtaining a first training result; determining a target threshold and a target variable type, carrying out clustering processing on multiple groups of meteorological data samples to obtain a first target category to which each group of meteorological data samples belong, carrying out wavelet decomposition on historical power generation power, training multiple initial power prediction models by adopting the target meteorological samples and the power signal samples under each |
---|---|
Bibliography: | Application Number: CN202210387225 |