电力用户用电特征选择与行为画像

User Electricity Consumption Feature Selection and Behavioral Portrait

我国交直流大电网的安全稳定运行与新能源的消纳对需求侧响应提出了较高要求,电力用户画像对需求侧响应的实施具有重要意义。文章提出了一种电力用户用电特征选择与行为画像方法。首先,通过构造聚合回报指标,兼顾集聚度和分离度,实现了最优分类数目的自动确定,并在此基础上完成k-means聚类;然后,将最大相关最小冗余准则应用于电力用户用电特征选取,兼顾了有效性和精简性,通过遍历法求得优质特征集;再采用打分制对优质特征进行量化,通过雷达图和柱状图等进行展示,实现了用户用电行为画像。最后通过算例分析表明了所提方法的有效性。

The stable operation of China’s AC/DC bulk power grid and the accommodation of renewable energy put forward high requirements on the demand response. User portrait is of great significance to the implementation of the demand response. Therefore, a method of user electricity consumption feature selection and behavioral portrait is proposed in this paper. Firstly, the clustering return index is constructed, in which taking into account the degree of aggregation and separation, the optimal cluster number is obtained automatically and k-means clustering is completed. Then, the maximal relevance and minimal redundancy(mRMR) criterion is applied to the selection of user electricity consumption features, in which the high-quality feature set is obtained by using enumeration method. Finally, the highquality features are quantified by the scoring method, and a radar map and a histogram are used to show the users electricity consumption behavior portrait. The results of an example show that the proposed method is effective.