Regional energy internet optimization method and device based on deep learning

Regional energy internet optimization method and device based on deep learning

The invention relates to a regional energy internet optimization method and device based on deep learning, and the method comprises the steps: 1, constructing a deep full-connection neural network, and carrying out the network parameter setting: determining the optimal number of hidden nodes of a ne...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SU SHIYANG, YANG YAOZHONG, LIANG GANG, JIANG YUE, HE ZHIXUAN, WANG YU, MA ZHANJUN, TIAN ZHEN, GUO SANLI, DANG XUXIN, WANG QUN, HE WEI, LIANG CHENG, CAO JING, JIANG LIYUAN, ZHANG WEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
PHYSICS
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 relates to a regional energy internet optimization method and device based on deep learning, and the method comprises the steps: 1, constructing a deep full-connection neural network, and carrying out the network parameter setting: determining the optimal number of hidden nodes of a network hidden layer through employing a trial and error method; 2, training a deep full-connection neural network by using historical data of equipment to obtain a deep agent; 3, constructing a regional energy internet optimization model considering the real-time working condition: detecting the real-time working condition: arranging detection equipment on the edge side of the regional energy internet, and detecting the real-time working condition of different equipment; according to the real-time working condition, selecting a deep agent from a historical database or utilizing the deep agent to output a current optimization parameter; and performing regional energy internet optimization calculation by using the cur