Training method and device of power grid load prediction model

The invention provides a training method and device for a power grid load prediction model, and the method comprises the steps: obtaining historical load data which comprises the load data of each time point in a past preset time length; under the condition that the load data at any time point is mi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	YOU SHANSHAN, ZHOU YONG, LI JINGTAO, HUANG LEI, YANG HAN, WANG FEI, YANG YANG, ZHOU NAIKANG, YUAN JIANLI, DAI BIYAN
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES HANDLING RECORD CARRIERS IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The invention provides a training method and device for a power grid load prediction model, and the method comprises the steps: obtaining historical load data which comprises the load data of each time point in a past preset time length; under the condition that the load data at any time point is missing, supplementing the load data at any time point; determining the load data of each date based on the supplemented load data of each moment point; under the condition that the load data of any date is missing, supplementing the load data of any date according to the date type and the annual power load growth rate; determining load data of each month according to the supplemented load data of each date; determining input data corresponding to each training month according to the load data of each month; and inputting the input data corresponding to each training month into the initial kernel SVR model for solving and training to obtain a kernel SVR model. The method is suitable for medium-and-long-term electrica