电力短期负荷的多嵌入维一阶局域预测

在混沌理论中,采用不同的嵌入维数计算方法所获得的维数略有不同,而在不同嵌入维数下对同一负荷时间序列进行预测的结果也不同,对此,文章提出了多嵌入维数的负荷预测方法,将不同维数下的预测结果进行加权平均;在预测过程中欧氏距离极限的取值对预测结果有很大影响,文中采用动态调整法进行选取以使预测误差最小.实例分析表明文章所提出的方法简单有效、具有可行性.

SHORT-TERM LOAD FORECASTING USING ONE-RANK LOCAL-REGION METHOD IN MULTI-DIMENSION EMBEDDING PHASE SPACE

In chaotic theory there is a litter difference in the obtained dimension by different embedded dimension calculation methods, and under different embedded dimension the forecasting results for same time series of load are different too. For this reason, the authors propose a load forecasting method using multi-embedded dimension, i.e., applying the weighted average to forecasting results under different dimension. Because the values of Euclid distance limits used in the forecasting evidently impact the forecasting results, so in this paper the value of Euclid distance limit is chosen by dynamic adjustment method to make the forecasting error minimum. Analysis of practical examples shows that the proposed method is simple, effective and feasible.