Short-Term Electricity Price Forecasting Based on PSO Algorithm and RBF Neural Network Algorithm

Author

Zhang Caiqing ; Ma Peiyu

Author_Institution

Dept. of Economic Manage., North China Electr. Power Univ., BaoDing, China

Volume

3

fYear

2010

fDate

13-14 March 2010

Firstpage

334

Lastpage

337

Abstract

A method of Radial Basis Function(RBF)neural network algorithm based on Particle Swarm Optimization (PSO) algorithm is introduced. In the background of PJM electricity market in the USA, the short-term price is forecasted with the historical price and loads. After determining the number, the center and width of the hidden layer, code the weights of output layer to individual particles and optimize them, then search the weight value of the best in the overall space. The result says that the new algorithm can improve the accuracy compared the traditional RBF network forcasting methods, so it has good application prospect.

Keywords

electricity supply industry; forecasting theory; particle swarm optimisation; power generation economics; power markets; pricing; radial basis function networks; PJM electricity market; PSO; RBF neural network; USA; particle swarm optimization; radial basis function neural network; short term electricity price forecasting; Artificial neural networks; Conference management; Economic forecasting; Energy management; Load forecasting; Neural networks; Particle swarm optimization; Power generation economics; Radial basis function networks; Technology forecasting; RBF neural network; elctricity system; particle swarm optimization; short-term eletrcity price forecast;

fLanguage

English

Publisher

ieee

Conference_Titel

Measuring Technology and Mechatronics Automation (ICMTMA), 2010 International Conference on

Conference_Location

Changsha City

Print_ISBN

978-1-4244-5001-5

Electronic_ISBN

978-1-4244-5739-7

Type

conf

DOI

10.1109/ICMTMA.2010.22

Filename

5459528