Short-term electrical load prediction method

A short-term electric load prediction method belongs to the technical field of electric power system load prediction, and comprises the following steps: carrying out abnormity processing and normalization processing on collected historical load data; performing clustering analysis on the historical load data by adopting a K-means method according to different correlation of time sequences of the historical load data; and performing oversampling processing and the like on the clustered data by using an SMOTE method. According to the invention, the characteristics of the input time sequence load data can be effectively learned, the load value is predicted more accurately, and the short-term load prediction precision is improved. 一种短期电负荷预测方法，属于电力系统负荷预测技术领域，包括如下步骤：对采集到的历史负荷数据进行异常处理及归一化处理；按照历史负荷数据时间序列不同的相关性,采用K-means方法对历史负荷数据进行聚类分析；利用SMOTE方法对聚类后的数据进行过采样处理等。本发明能够有效的学习输入时间序列负荷数据的特征，更准确的预测负荷值，提高了短期负荷预测的精度。