关键词: 多变量时间序列，相空间重构，短期负荷预测，正则化回归

Abstract: Regulation regression local forecasting method of multivariable chaotic time series in short term electricalload was proposed, in order to improve the forecasting accuracy of short-term electrical load. The multivariate time series were constructed, by choosing the effective temperature factors with the greatest impact on the load. Firstly, time delay and embedding dimension were confirmed with the methods of mutual information and the minimum predicting error. Secondly, according to reconstruction parameters, the phase space of short term load multivariate time series was reconstructed. Thirdly, aiming at few neighboring points in the partial predicting method that can not satisfy least square estimate condition, multivariate time series chaos partial forecasting model based on the regularized regression was presented. Moreover, such model was carried on in practical power load forecast(an electrical power in Chongqing)，and the forecasting accuracy was enhanced.

Key words: Multivariate chaotic time series, Phase space reconstruction, Short term load forecasting, Regulation regression