一种基于组合算法的异常用电模式辨识方法

针对电力用户异常用电的检测问题，提出了一种基于无监督组合算法的异常用电模式辨识方法。所提辨识方法由数据处理、特征提取、离群检测三部分组成。文中先获取用户的用电量及相关数据，进行数据清洗和缺失数值补全；再对数据进行特征提取，得到相应的异常用电识别特征量；通过k均值聚类将用户聚为两组，并分别对每组进行主成分分析优化特征空间，计算离群邻近度，通过2 sigma原则实现异常用电用户辨识。该方法通过聚类、优化特征空间、离群检测组合算法，提高了辨识效率。文中采用真实用电数据进行了异常用电用户辨识仿真实验，辨识结果验证了该方法的有效性。

Identification of Abnormal Power Consumption Mode Based on Combination Algorithm

In a bid to detect abnormal electricity consumption of power users, a method for identifying abnormal electricity consumption mode based on unsupervised combination algorithm was proposed. The proposed identification method consists of three parts: data processing, feature extraction and outlier detection. Firstly, the power consumption and related data of the users are obtained, and the data is cleaned and the missing value is supplemented. Then feature extraction is carried out on the data to obtain the corresponding features for abnormal electricity use recognition. Afterwards, k_ means was used to cluster the users into two groups, and principal component analysis was performed on each group to optimize the feature space. Lastly, the outlier proximity is calculated, and abnormal power users were identified by 2 sigma principle. This method improves the identification efficiency by combining clustering, optimization of feature space and outlier detection. The simulation experiment of abnormal power user identification is carried out with real power consumption data, and the identification results verify the effectiveness of the method.