Outlier Detection Model of Electric Power Big Data Based on Fuzzy K-means Clustering Algorithm

Abnormal operation of big data in electric power will affect users' normal electricity consumption, increase of line loss and loss of electricity, or even cause fire, affect the stability and security of power grid, and bring serious economic loss and reputation loss to power grid enterprises. In this paper, based on fuzzy K-means clustering algorithm, the outlier detection of power big data is studied, and the outlier detection model of power big data is established. Finally, through the simulation experiment, it can be found that the number of detection results based on fuzzy K-means clustering algorithm is reduced compared with the actual results, and it also shows good performance in the face of data from multiple transformers with different magnitude of data, which shows that the algorithm can be applied to larger data sets. Compared with the density-based detection algorithm, the algorithm in this paper is more feasible, and it can better realize power big data fusion and anomaly detection, so it is worth popularizing and applying. The basic idea of the power big data outlier detection model based on fuzzy K-means clustering algorithm is to optimize the initial clustering center, improve the complexity of power big data outlier detection, and improve the detection accuracy and efficiency.