Title :
Price Forecasting Based on PSO Train BP Neural Network
Author :
He, Yong Gui ; Bo, Li
Author_Institution :
Dept. of Econ. Manage., North China Electr. Power Univ., Baoding
Abstract :
In this paper, the basic idea is to use percent of reserve capacity, the historical load and price to forecast short-term electricity price .The paper provides an example of bidding model to forecast market clear price using BP neural network trained by PSO. To compare with the result of traditional BP neural network, the proposed method has better forecasting precision and can convergence to global optimal solution at all times.
Keywords :
backpropagation; convergence; neural nets; particle swarm optimisation; power engineering computing; power markets; power system economics; pricing; PSO train BP neural network; bidding model; convergence; electricity market; market clear price; price forecasting; reserve capacity; Economic forecasting; Electricity supply industry; Energy management; Load forecasting; Management training; Neural networks; Power generation; Predictive models; Recurrent neural networks; Time series analysis;
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.2009.4918628
