Title :
IPSO-BP hybrid prediction model and its application in power load
Author :
Shao, Yuxiang ; Xu, Hongwen
Author_Institution :
Sch. of Comput. Sci. & Technol., China Univ. of Geosci., Wuhan, China
Abstract :
This paper presents a new BP neural network (BP NN) forecast model named IPSO-BP forecast model that is based on an improved particle swarm optimization (IPSO). The improved PSO employs parameter with crossover operator and mutations operator to significantly improve the performance of the original PSO algorithm in global search and fine-tuning of the solutions. This study uses the IPSO algorithm to optimize authority value and threshold value of BP nerve network, so IPSO-BP neural network algorithm model has been established and applied into the power load forecast. The results demonstrate that this model has significant advantages inspect of fast convergence speed, good generalization ability and not easy to yield minimal local results.
Keywords :
backpropagation; load forecasting; neural nets; particle swarm optimisation; power engineering computing; IPSO-BP hybrid prediction model; backpropagation neural network; particle swarm optimization; power load forecasting; Acceleration; Application software; Genetic mutations; Geology; Load forecasting; Neural networks; Particle swarm optimization; Predictive models; Space technology; Technology forecasting; Generalization; IPSO-BP Neural Network; Optimization; Power Load;
Conference_Titel :
Computer Science and Information Technology, 2009. ICCSIT 2009. 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4519-6
Electronic_ISBN :
978-1-4244-4520-2
DOI :
10.1109/ICCSIT.2009.5234545