Multi-dimensional energy efficiency assessment of residential users based on big data analysis of differentiated electricity consumption behavior

With the development and application of advanced measurement systems and power distribution information collection systems, user-side data has increased geometrically. In the face of massive data, mining and using user-side data characteristics is one of the main problems of current big data analysis. In this paper, one month's load data of users in a residential area in Shandong is used as a research sample. Firstly, the characteristics of electricity consumption are analyzed, the feature set of electricity consumption behavior is established, and the feature extraction and dimension reduction are carried out by the PCA method in this paper. Then, the users' electricity consumption behavior is clustered, the users are divided into five categories, and the characteristics are analyzed and compared; Finally, based on the entropy weight method, comprehensive energy efficiency assessment is performed for residential users, and its comprehensive energy efficiency is evaluated from horizontal and vertical perspectives, combined with the characteristics of electricity consumption. The results of this paper provide help for further data analysis and application of power demand load forecast analysis, differentiated services, etc.