New energy power prediction method based on multivariable meteorological factors

The invention provides a new energy power prediction method based on multivariable meteorological factors, and the method comprises the steps: judging the linear correlation between the new energy generating capacity and the meteorological factors, and building a data set of the generating capacity...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: LIU XIANZHUO
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides a new energy power prediction method based on multivariable meteorological factors, and the method comprises the steps: judging the linear correlation between the new energy generating capacity and the meteorological factors, and building a data set of the generating capacity and the meteorological factors; establishing a multiple linear regression model according to the data set of the generating capacity and the meteorological factors; meteorological factor forecasting data are obtained, and deterministic forecasting is carried out through the regression model; performing uncertainty forecasting and probability forecasting according to meteorological factor forecasting errors; constructing a convolutional neural network model, and establishing a nonlinear implicit mapping relation between the meteorological field and the new energy generating capacity; establishing a new energy generating capacity prediction model combining linear regression and a convolutional neural network; adjusti