基于大数据分析的电力用户行为画像构建方法研究

Research on Construction Method of Power User Behavior Portrait Based on Big Data Analysis

为了解居民电力用户是否具备调控潜力,分析不同时间段居民电力用户用电情况,提高居民电力用户行为画像准确率为目的,提出基于大数据分析的电力用户行为画像构建方法。通过采集用户用电行为相关的真实数据,建立包含用户基本信息、用电行为、用电特性与缴费行为标签的用户行为标签库;利用改进K均值聚类算法分析用户行为簇别,根据簇别的降序实施目标用户群的筛选,根据居民电力用户不同行为标签与总体调控簇别的划分结果构建用户画像,并以可视化方式呈现。实验结果证明:所研究方法可有效分析出不同时间段的居民电力用户的用电情况,所构建的用户画像准确率较高,可以精准找出具备调控潜力的居民电力用户。

For understanding whether the residential power users have regulatory potential,analyzing power consumption of residential power users in different periods of time and improving accuracy of the power user behaviour portrait,a construction method of power users behavior portrait based on big data analysis is proposed. By collecting the real data related to the user’s electricity consumption behavior,a user behavior tag library containing the basic information of users,electricity consumption behavior,electricity consumption characteristics and payment behavior tags is established. The user behavior clusters are analyzed by using the improved k-means clustering algorithm,and the target user groups are screened in accordance with the descending order of the clusters. The user portrait is constructed in accordance with the different behaviour tag of the power user and the classification result of general control cluster results and is shown in a visual way. The experimental results show that the research method can effectively analyze the power consumption of residential power user in different periods of time,the accuracy of the constructed user portrait is higher and the residential power user with regulatory potential can be accurately identified.