DocumentCode
2047906
Title
Electric load forecasting using structure variable neural networks
Author
Han, M.X. ; Xu, Z.H. ; Yu, Y.Y.
Author_Institution
Beijing Graduate Sch., North China Inst. of Electr. Power, China
Volume
5
fYear
1993
fDate
19-21 Oct. 1993
Firstpage
355
Abstract
Based on the new developed structure variable neural networks, two models-the daily peak load (DPL) model and daily 24-hour load (DHL) model are proposed in the present paper. The cluster Gaussian analysis (CGA) is used for the training of the models. The effectiveness of the new forecasting strategy is demonstrated by training and testing using the data collected from the Jing-Jin-Tang network.<>
Keywords
backpropagation; load forecasting; neural nets; power system analysis computing; power system control; power system protection; Jing-Jin-Tang network; backpropagation; cluster Gaussian analysis; daily 24-hour load model; daily peak load model; electric load forecasting; model training; power system operation; power system security; structure variable neural networks; Artificial neural networks; Load forecasting; Load modeling; Model driven engineering; Neural networks; Page description languages; Predictive models; Temperature; Tires; Weather forecasting;
fLanguage
English
Publisher
ieee
Conference_Titel
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location
Beijing, China
Print_ISBN
0-7803-1233-3
Type
conf
DOI
10.1109/TENCON.1993.320656
Filename
320656
Link To Document