Research of short-term load forecasting algorithm based on wavelet analysis and radial basis function neural network

To improve the accuracy of load forecasting, a new algorithm is presented to forecast the short-term load. In the paper, short-time load sequence of the power supply system composed by different frequency signals is decomposed into the signals on different frequency bands by wavelets. Then the Radia...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu-Jian Chang, Shuo-He Wang, Hai-Yan Sun
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Clustering algorithms
Function approximation
Intelligent transportation systems
Load forecasting
Neural networks
Power system
Prediction algorithms
Predictive models
Radial basis function networks
RBF Neural Network
Wavelet analysis
Wavelet theory
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To improve the accuracy of load forecasting, a new algorithm is presented to forecast the short-term load. In the paper, short-time load sequence of the power supply system composed by different frequency signals is decomposed into the signals on different frequency bands by wavelets. Then the Radial Basis Function neural network (RBFNN) is used to forecast these signals in every scale space, and then this sequence is reconstructed. The average forecasting errors which are got by Haar Wavelet and RBFNN prediction model are about 7.7%. Compared with BP neural network prediction model, it has the more accurate partial prediction results. Therefore, the prediction errors of Haar wavelet and RBFNN prediction model are acceptable.
DOI:10.1109/PEITS.2009.5406961