期刊文献+

基于Elman网络的电力负荷预测研究 被引量:2

Research on Electric Load Forecasting Based on Elman Neural Networks
在线阅读 下载PDF
导出
摘要 电力系统负荷与诸多影响因素之间是一种强耦合、多变量、严重非线性的关系,且这种关系具有动态性。传统预测方法精度不高,而采用动态回归神经网络(Elman)能更直接、更有效地反映系统的动态特性。该文建立了基于Elman神经网络的电力负荷预测模型,通过MATLAB仿真预测,对比Elman神经网络和BP神经网络的预测效果。仿真实验证明了Elman神经网络具有良好的动态特性、较快的训练速度、高精度等特点,表明Elman预测模型是一种新颖、可靠的负荷预测方法。 The relationship between the load of power system and other influencing factors is strong coupling,multivariable,very non-linear,and dynamic.Traditional prediction cannot realize high accuracy,while dynamic recurrent nerve network(Elman) can reflect the dynamic nature of the system in a more direct and effective way.A prediction model of power load was established based on Elman neural network in this paper.By cases of prediction,the modeling effect of Elman network and BP network structure was compared.Simulation experiment shows that Elman neural network bears features such as dynamic,fast in network training and high accuracy,which proves that Elman prediction model is a fresh and reliable way of power load prediction.
作者 井望隆 潘玉民 JING Wang-long,PAN Yu-min(College of Electronic Information Engineering,North China Institute of Science and Technology,Beijing 101601,China)
出处 《电脑知识与技术》 2013年第6期3871-3874,共4页 Computer Knowledge and Technology
基金 河北省教育厅科学技术研究项目(编号:Z2006439)
关键词 电力负荷 ELMAN网络 BP网络 预测 power load load prediction neural network Elman network
作者简介 井望隆(1989-),男,黑龙江勃利人,学士,主要研究方向为神经网络、智能控制; 潘玉民(1958-),男,硕士,副教授,主要研究方向为模式识别、复杂系统建模。
  • 相关文献

参考文献7

二级参考文献23

  • 1邵莹,高中文.基于模糊集理论的短期电力负荷预测[J].信息技术,2005,29(5):18-20. 被引量:10
  • 2[1]M.I.Jordan,Attractor dynamics and parallelism in a connectionist sequential machhine"[C].Proceedings of the 8th Conference on Cognitive Science,1986:531-546.
  • 3[2]Jeffrey L.Eleman.Finding Structure in Time[J].Cognitive Science,1990,14:179-211.
  • 4[3]Levis.A.U,Narendra K.S.Control of nonlinear dynamical systems using neural networks-partⅡ:observability,identification,and contral[J].IEEE Trans on Neural Networks,1996,7(1):30-42
  • 5[4]G.Cybenko.Approximation by Superposition of a sigmoid function[J].Mathematics of Control,Signals and Systems,1989,2(3):303-314.
  • 6[5]J.W.Dong,J.X.Qian and Y.X.Sun.Recurrent neural networks for recursive identification of nonlinear dynamic process[C].Proceedings of the IEEE Intemational Conference on Industrial Technology,1994:794-798.
  • 7[6]D.P.Kwok,P.Wang,and K.Zhou.Process identifyieation using a modified Eleman neural network[C]International Sympoeium on Speech,Image Proeessing and Neural Networks,1994:499-502.
  • 8[7]X.Z.Gao,X.M.Cao,and S.J.Ovaska,A modified Eleman neural network model with application to dynamical systems identifyieation[C].Proceedings of IEEE International Conference on System,Man and Cybeme1996(2):1376-1381.
  • 9[8]W.Chagra,R B.Abdennour,F.Bouani,F.Bouani,M.Ksouri,and G.Favier.A Comparetive study on the channel modeling using feedforward and recurrent neural network structures[C].Proeeedings of the IEEE International Confemaee on System,Man and Cybemetics,1998(4).3785-3763.
  • 10[9]J.E W.Holm and N.J.H.Kotze.training recurrent neural networks with leapfrog[C].Proceeding of the International Conference on Industrial Electronics,1998,99-104.

共引文献55

同被引文献7

引证文献2

二级引证文献33

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部