2007, Volume 9, Issue 5
Strategic Study of CAE >> 2007, Volume 9, Issue 5
Short-term Load Forecasting Using Neural Network
Shaanxi Textile and Garment Institute, Xianyang, Shaanxi 712000, China
Next Previous
Abstract
Based on the load data of meritorious power of some area power system, three BP ANN models, namely SDBP, LMBP and BRBP Model, are established to carry out the short-term load forecasting work, and the results are compared. Since the traditional BP algorithm has some unavoidable disadvantages, such as the low training speed and the possibility of being plunged into minimums local minimizing the optimized function, an optimized L-M algorithm, which can accelerate the training of neural network and improve the stability of the convergence, should be applied to forecast to reduce the mean relative error. Bayesian regularization can overcome the over fitting and improve the generalization of ANN.
Keywords
short-term load forecasting(STLF) ; ANN ; Levenberg-Marquardt ; Bayesian regularization ; optimized algorithms
Figures
图 1
图 2
图 3
图 4
图 5
References
[ 1 ] Hagan M T ,Demuth H B , Beale M H . Neural Network design[M] . 戴 葵 ,等译 .北京 :机械工业出版社 , 2002 .201 ~ 205
[ 2 ] Hornik K M , Stinchcombe M , White H . Multilayer feedforward networks are universal approximators [ J] . Neural Networks ,1989 ,2(5) :359 ~ 366 link1
[ 3 ] Hinton G E . Connectionist learning procedures [ J ] . Artificial Intelligence ,1989 ,40 :185 ~ 234 link1
[ 4 ] Weigand A S , Rumelhart D E , Huberman B A . Generalization by weight elimination with application to forecasting [ A ] . Advances in Neural Information Proceeding Systems 3 [C] . In : Lippman R , Moody J , touretzky D , eds . San Mateo , CA : Morgan Kaufmann , 1991 ,575 ~ 582 link1
[ 5 ] 许 东 ,吴 铮 .基于 MATLAB6 .X 的系统分析与设 计 ——— 神经网络[M] .第二版 .西安 :西安电子科技 大学出版社 ,2002 .186 ~ 194
京公网安备 11010502051620号
