Open AccessTheoretical Framework of Energy Internet Demand Forecasting Based on Internal and External Information Fusion
Author(s) -
Shaofei Jiang,
Weihong Yang,
Zhili Wu,
Yanan Cao,
Ming Zhang,
Pengjia Shi
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1769/1/012028
Subject(s) - the internet , computer science , demand forecasting , energy (signal processing) , perspective (graphical) , data mining , feature (linguistics) , layer (electronics) , data science , operations research , artificial intelligence , engineering , world wide web , linguistics , statistics , philosophy , chemistry , mathematics , organic chemistry
Due to the limited information sources, the existing energy demand forecasting models cannot fully, truly and accurately reflect the nature of the trend change of Energy Internet demand. To solve this problem, this paper establishes a theoretical framework of Energy Internet demand forecasting based on internal and external information fusion from the perspective of information sources. The framework summarizes the data characteristics of energy internet and divides the data information into internal information and external information. According to the attribute characteristics of data information, the forecasting information is divided into data layer, feature layer and decision layer. Finally, a combined forecasting model is established for data at different levels for data forecasting. The framework uses multi-source information fusion prediction theory to fuse the internal and external prediction information of energy Internet in different situations, which increases the amount of information of the prediction model.