中长期电力负荷预测的集对分析聚类算法

Set Pair Analysis Classified Prediction Method for Medium and Long-term Load Forecasting

提出了一种中长期电力负荷预测的集对分析聚类算法。该方法采用集对分析中的同异反模式进行模式识别,并根据聚类分析的基本思想进行分类预测。最后采用福建省年用电量数据进行了实例研究,结果表明该预测方法是有效的。

In this paper, the set pair analysis classified prediction method is applied to medium and long-term power load forecasting. The IRO （Identity Resemblance Opposition） pattern in pair analysis is used for pattern recognition and the basic idea of cluster analysis is used for classification and prediction. Finally, the effectiveness of the proposed method is evaluated by applying it to load demand forecast in Fujian Province. The forecasting results show that the method is feasible and effective.