Analysis of user electricity consumption behavior based on density peak clustering with shared neighbors and attractiveness

Abstract

Summary User behavior analysis is the research foundation of power load forecasting and power abnormal detection, and it is the theoretical support for smart grid planning and the construction of energy internet. Aiming at the complex characteristics of high‐dimensional, noisy, and multi‐redundant of power load data, this article used the principal component analysis (PCA) to reduce the dimensionality of power data. The density peaks clustering algorithm with shared neighbor and attractiveness (DPC‐SNA) was then used to cluster the data with reduced dimensionality to extract the user's electricity consumption characteristics. The DPC‐SNA algorithm first constructs a sample similarity measurement criterion that shares the similarity of neighbors, on which the local density is defined accordingly. The new local density can effectively distinguish the contributions of local samples and global samples. Incorporating the idea of universal gravitation, a new calculation method of sample attractiveness was defined, and the remaining samples were allocated by the attractiveness matrix. Experiment was performed using the actual load data of special transformer users in a certain area. The results show that there were five typical electricity consumption behavior characteristics in this area, namely, the evening‐peak production type, all‐day production type, multi‐peak production type, daytime production type, and night production type. The corresponding load peak time periods were also obtained.

Research on the double-layer clustering method of residential energy use characteristics under the background of energy system energy savings and carbon reduction

“…In the context of power big data, simply increasing the supply-side capacity to meet the growing user load and peak electricity demand will cause a series of problems, such as low annual utilization hours of power generation and transmission equipment, high cost, and waste of social resources (Liu et al, 2014;Xu et al, 2023). Although the proportion of users participating in demand response is increasing year by year, due to the large number of participating users and complex load types, it is difficult to accurately distinguish and predict the energy use information and response potential of users (Xu et al, 2018;Li et al, 2022), resulting in an unsatisfactory effect of demand response, which has had a significant impact on the economy and life of both supply and demand. Therefore, on account of the two aspects, namely, user electricity consumption data and user household characteristics, analyzing user energy consumption behavior can achieve precise differentiation of load regulation potential for user energy consumption characteristics and demand response.…”

“…This method can calculate the centralized power consumption of large users, and at the same time, the behavior pattern characteristics of users can be extracted in a directional manner, and power resources can be allocated according to demand. Li et al (2021) proposed a user electricity behavior detection method based on singular spectrum analysis, which involves performing singular spectrum analysis on the user's electricity behavior before and after the detection point. Accurate judgment of electricity behavioral changes can be achieved by calculating the cosine value of the angle between the singular value vector and the historical feature hyperplane.…”