Cloud platform operation data preprocessing method based on I-GMM algorithm

The invention discloses a cloud platform operation data preprocessing method based on an I-GMM algorithm. The method comprises the steps that an intelligent power grid cloud platform is built according to a cloud computing architecture; performing data cleaning on the stored original power grid data...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SUN JIANGANG, CHANG YUZHU, GONG SHUAI, LI MING, LI JING, MAO DONG, GAO FENG, GE BINGYU, LAI FENGGANG, XUAN JIAXING, DUAN TINGTING, GAO YING, YIN XIAOYU, RAO HANYU, QIAO YUJIE, LIU YUECAN, CHENG QING, LEI TING
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 discloses a cloud platform operation data preprocessing method based on an I-GMM algorithm. The method comprises the steps that an intelligent power grid cloud platform is built according to a cloud computing architecture; performing data cleaning on the stored original power grid data on the intelligent power grid cloud platform, and performing missing value completion and data normalization operation on the original power grid data in sequence; and constructing a power grid data classification model based on a Gaussian mixture model, classifying the real-time power grid data after data cleaning by adopting the power grid data classification model, and respectively storing the real-time power grid data to each module of the intelligent power grid cloud platform according to categories. According to the method, the data in the smart power grid can be continuously preprocessed and then classified and stored, so that the data quality can be greatly improved, the calculation time and storage space