Title :
Research of the Load Forecasting Model Base on HHT and Combination of ANN
Author :
Bai, Weili ; Liu, Zhigang ; Zhou, Dengdeng ; Wang, Qi
Author_Institution :
Coll. of Electr. Eng., Southwest Jiaotong Univ., Chengdu
Abstract :
A. new forecasting model based on HHT and combination of ANN is proposed in the paper. Load data can be decomposed into several IMF components and remainder by EMD firstly. Through calculating the spectrum of decomposed series by Hilbert transform algorithm, we can choose one appropriate forecasting model for each low frequency component, while use combination of ANN model for the high frequency component, according to low frequency components having stronger regularity and periodicity than high frequency components. Simulation results indicate that accuracy of the forecasting model discussed in the paper is higher than any one sole model and the traditional linear combination model.
Keywords :
Hilbert transforms; load forecasting; neural nets; ANN; EMD; HHT; Hilbert-Huang transform; artificial neural network; empirical mode decomposition; load forecasting model; Data analysis; Educational institutions; Electronic mail; Frequency; Load forecasting; Load modeling; Power system analysis computing; Power system modeling; Power system simulation; Predictive models;
Conference_Titel :
Power and Energy Engineering Conference, 2009. APPEEC 2009. Asia-Pacific
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-2486-3
Electronic_ISBN :
978-1-4244-2487-0
DOI :
10.1109/APPEEC.2009.4918671