Genetic Algorithm-Based RBF Neural Network Load Forecasting Model

Author

Zhangang, Yang ; Yanbo, Che ; Cheng, K. W Eric

Author_Institution

Sch. of Electr. Eng. & Autom., Tianjin Univ., Tianjin

fYear

2007

fDate

24-28 June 2007

Firstpage

1

Lastpage

6

Abstract

To overcome the limitation of the traditional load forecasting method, a new load forecasting system basing on radial basis Gaussian kernel function (RBF) neural network is proposed in this paper. Genetic algorithm adopting the real coding, crossover probability and mutation probability was applied to optimize the parameters of the neural network, and a faster convergence rate was reached. Theoretical analysis and simulations prove that this load forecasting model is more practical and has more precision than the traditional one.

Keywords

genetic algorithms; load forecasting; power engineering computing; probability; radial basis function networks; crossover probability; genetic algorithm-based RBF neural network; load forecasting model; mutation probability; radial basis Gaussian kernel function; Convergence; Genetic algorithms; Load forecasting; Load modeling; Neural networks; Power system modeling; Power system planning; Power system reliability; Predictive models; Radial basis function networks; Convergence Rate; Genetic Algorithm; Load Forecasting; RBF Neural Network; Real Coding;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Engineering Society General Meeting, 2007. IEEE

Conference_Location

Tampa, FL

ISSN

1932-5517

Print_ISBN

1-4244-1296-X

Electronic_ISBN

1932-5517

Type

conf

DOI

10.1109/PES.2007.385710

Filename

4275476