Anomaly Detection Of State Information Of Power Equipment Based On Big Data Analysis

The anomaly detection of power equipment plays an important role in the safe and stable operation of power grid.Detecting anomalies in power equipment is helpful to the discovery of problems during operation of power grid and solution to make through the problem.Big data technology has been applied in many fields including the internet and finance.But in the power field,the application is still in the exploration stage.This paper suggests to use big data technology in anomaly detection of power equipment.The equipment state information can be used comprehensively and effectively.The detection result will become more reliable and accurate.The detection provides the basis for the next step of repair work.In this paper,the influence of various kinds of information on the operation of the transformer and transmission line is analyzed.Appropriate state variables are selected to describe the operation of the transformer and transmission line.According to the practical experience,the health level of the transformer and transmission line is divided.State evaluation system of equipment is established based on scientific principal,which lay the foundation for the assessment of state.In view of the fact that the traditional anomaly detecting methods for power equipment do not consider the spatial information of the state data,this paper proposes a method for anomaly detection of state data of power equipment based on spatiotemporal clustering method,which employs historical big data of the equipment state and meteorological environment and makes visualization of the equipment states in process.The detail of the method is as follows: With a sliding window,the time series are divided into a number of subsequences which will be combined with space coordinates to form spatiotemporal data;the available spatiotemporal structure within each time window is discovered using the FCM method,and an anomaly score is assigned to each cluster,whose value determines whether the cluster is anomalous or not;then the visualization of a propagation of anomalies occurring in consecutive time intervals is realized by using a fuzzy relation formed between revealed structures.At last,the effectiveness of the method is verified by an example.Load capacity of transformer is analyzed and the anomaly is detected.Data of historical environmental temperature and load factor of transformer is collected,which is used to predict the future state several hours later using RBF neural network.The prediction results are put into the hot spot temperature calculation model to get the final forecast of the hot spot temperature of transformer in the next few hours.The load capacity of transformer is effectively evaluated.The data of sampled environmental temperature,load and hot spot temperature is clustered using fuzzy c-means cluster method.Anomaly scores are set according to the distances between the data points to their clustering center.Whether the data point is anomalous or not is judged by the value of anomaly score.