Electric load prediction method and system for industrial area

The invention relates to the technical field of cloud edge collaboration, in particular to an electrical load prediction method and system for an industrial area, and is applied to a cloud server. Comprising the following steps: receiving a non-uniform continuous time hidden semi-Markov model sent b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHENG HONGJUAN, YU HANG, LIU YONGCHUN, ZHANG WEIGUO, LU ZHENJUN, GU LINLIN, LI HUA, WAN ZECHEN, FANG JIAWEI, SHAO YUNFENG, YANG PING, XING SIHAO, ZHU QING, JIANG XINTONG, LIN HUIJIE
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 relates to the technical field of cloud edge collaboration, in particular to an electrical load prediction method and system for an industrial area, and is applied to a cloud server. Comprising the following steps: receiving a non-uniform continuous time hidden semi-Markov model sent by N edge computing terminals, and decrypting the non-uniform continuous time hidden semi-Markov model; according to the preliminarily encrypted power utilization load prediction vector of the power utilization factory and the randomly generated password, restoring to obtain a predicted future power utilization load of the power utilization factory and a weight and a threshold of the power utilization load prediction model of the power utilization factory, wherein the weight and the threshold meet a preset precision requirement; training an industrial area power load prediction model according to the future power load and the weight value and the threshold value meeting the preset precision requirement; and repeatin