DocumentCode :
3465996
Title :
Application of wavelet and neural network to long-term load forecasting
Author :
Khoa, T.Q.D. ; Phuong, L.M. ; Binh, P.T.T. ; Lien, N.T.H.
Author_Institution :
Electr. & Electron. Eng., Ho Chi Minh City Univ. of Technol., Vietnam
Volume :
1
fYear :
2004
fDate :
21-24 Nov. 2004
Firstpage :
840
Abstract :
Long term load forecasting presents the first step in planning and developing future generation, transmission and distribution facilities. Artificial intelligent applications have been introduced for load forecasting. The forecasting procedure considered the correlation variables that have an influence over the demand for electricity, for example: gross state product (GSP), consumers price index (CPI) and electricity tariff (ET). These variables are chosen to enter the model as the inputs of network. The output is consumed energy. This paper proposed to apply the universal approximation properties of neural and wavelet networks to determine the function that denote relationship between input variables and output energy. The basic back-propagation algorithm is used as a supervisory learning. Three network models are proposed in this paper: functional link net, multi-layer perceptron neural network and wavelet network.
Keywords :
backpropagation; load forecasting; multilayer perceptrons; power engineering computing; power system economics; wavelet transforms; artificial intelligent applications; back-propagation algorithm; consumers price index; correlation variables; electricity tariff; functional link net; gross state product; long-term load forecasting; multilayer perceptron neural network; supervisory learning; universal approximation properties; wavelet network; Artificial neural networks; Discrete wavelet transforms; Energy consumption; Least squares approximation; Load forecasting; Multi-layer neural network; Multilayer perceptrons; Neural networks; Power system planning; Power system reliability;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power System Technology, 2004. PowerCon 2004. 2004 International Conference on
Print_ISBN :
0-7803-8610-8
Type :
conf
DOI :
10.1109/ICPST.2004.1460110
Filename :
1460110
Link To Document :
بازگشت