电网短期负荷预测的混沌方法

通过计算四川全省电网小时负荷时间序列的混沌特征量：饱和关联维数、最大Lyapunov指数和Kolmogorov熵，论证了该小时负荷序列属于混沌时间序列。以负荷相空间重构为前提，分别应用混沌分析法的相似点模型、线性回归模型及Lyapunov指数模型对其短期负荷预测，并对比了三种模型预测的效果，预测结果表明了混沌预测方法的有效性。

Short Term Load Forecasting Using Chaotic Method

Chaotic characteristic quantity of hourly power load of Sichuan province is analyzed, that is, saturation correlation dimension, maximun Lyapunov exponent and Kolmogorov entropy, and it is concluded that hourly load time series belongs to chaotic series. Based on the phase space reconstruction theory, short term forecasting for hourly load is studied using neighbor model, linear regression model and Lyapunov exponent model respectively. The prediction results show that the chaotic method is effective for short term load forecasting.