Title :
Medium and Long-Term Load Forecasting Based on PCA and BP Neural Network Method
Author :
Shi Zhang ; Dingwei Wang
Author_Institution :
Inst. of Syst. Eng., Northeastern Univ., Shenyang, China
Abstract :
To settle the problem which the precision and generalization performance of forecast model is affected easily by input variable, the method which reconstructs the original input space of back-propagation neural network by principal component analysis that can eliminate the relevance of value is researched. The method can not only reduce duplicated information but also extract the leading factors. Its can also optimize its network structure as well as enhance the network´s forecast precision. The effectiveness of the proposed algorithm is verified by the practical data.
Keywords :
backpropagation; load forecasting; neural nets; optimisation; power systems; principal component analysis; BP neural network; PCA; back propagation neural network; duplicated information reduction; long term load forecasting; medium term load forecasting; network forecast precision; network structure optimization; power system; principal component analysis; Covariance matrix; Economic forecasting; Load forecasting; Matrix decomposition; Neural networks; Power engineering and energy; Power system planning; Power systems; Principal component analysis; Systems engineering and theory; back-propagation neural network(BPNN); load forecasting; power system; principal component analysis;
Conference_Titel :
Energy and Environment Technology, 2009. ICEET '09. International Conference on
Conference_Location :
Guilin, Guangxi
Print_ISBN :
978-0-7695-3819-8
DOI :
10.1109/ICEET.2009.559
