基于混沌时间序列和神经网络的电力短期负荷预测-电力系统及其自动化专业论文.docxVIP

选择时采用了该方法，建立了混合混沌关联度的神经网络预报模 选择时采用了该方法，建立了混合混沌关联度的神经网络预报模 型，并实例计算表明其能有效提高预测的精度。 最后，考虑到常用的混沌时序预测模型都是一种单步外推预 测，存在计算复杂和耗时的缺点，对此，提出了一种将分时段相 空间重构理论和广义回归神经网络相结合的短期负荷预测新方 法，实例证明了其有良好的预测效果。 关键词： 短期负荷预测 混沌时间序列 相空间重构 分时段 相空间重构 神经网络 广义回归神经网络 Short—Term Short—Term Load Forecasting Based on Chaotic Timel Series and NeuraII Networks Abstract Short—term load forecasting(STLF)is very important for the economical， stable，and secure operation of power systems，and it is a vital common work of distribution operation and load management．It’S proved that Short-term load is a multiple dimension nonlinear chaotic system under the influence of temperature，humidity，wind power，somber day or fine day，rainfall，feast day etc．and，It’S also proved that power load time series is a kind of chaotic time series．Under the reciprocity of various influencing factors，load become complexity and it’S hard to predict accurately．With the development of nonlinear theory，especially the development of chaotic theory，it’S possible that we can get satisfactory forecasting results without considering various influencing factors． Chaotic time series is a burgeoning study，predicting it is a hot study． Neural network is a kind of intellectualized technology．It is excel at dealing with nonlinear problem．Combining with the both will bring new problems． The paper combines chaotic time series with neural network，and apply it to Short-term load forecasting． Firstly，the paper，studies chaotic time series and phase space reconstruction technology，computes the best delay time and best embedding dimension for a practical power system’S Short—term load，and reconstructs phase space．Creating a forecasting model based chaotic time series and BP neural network，result analysis of practical examples shows that the proposed modeliS effective and feasible． Secondly，comparability can’t weight commendably using Euclid distance， III for for the shortcoming，best resemble phase points is presented in this paper，and weight commendably u