Anomaly Detection and Classification in Streaming PMU Data in Smart Grids

作     者：A.L.Amutha R.Annie Uthra J.Preetha Roselyn R.Golda Brunet 

作者机构：Department of Computational IntelligenceSRM Institute of Science and TechnologyChennai603203India Department of Electrical and Electronics EngineeringSRM Institute of Science and TechnologyChennai603203India Department of Computer Science and EngineeringGovernment College of EngineeringSalem636011India 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第46卷第9期

页      面：3387-3401页

核心收录：

学科分类：080802[工学-电力系统及其自动化] 0808[工学-电气工程] 08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Smart Grid PMU data incremental learning classifying anomalies artificial intelligence 

摘      要：The invention of Phasor Measurement Units(PMUs)produce synchronized phasor measurements with high resolution real time monitoring and control of power system in smart grids that make *** are used in transmitting data to Phasor Data Concentrators(PDC)placed in control centers for monitoring purpose.A primary concern of system operators in control centers is maintaining safe and efficient operation of the power *** can be achieved by continuous monitoring of the PMU data that contains both normal and abnormal *** normal data indicates the normal behavior of the grid whereas the abnormal data indicates fault or abnormal conditions in power *** a result,detecting anomalies/abnormal conditions in the fast flowing PMU data that reflects the status of the power system is critical.A novel methodology for detecting and categorizing abnormalities in streaming PMU data is presented in this *** proposed method consists of three modules namely,offline Gaussian Mixture Model(GMM),online GMM for identifying anomalies and clustering ensemble model for classifying the *** significant features of the proposed method are detecting anomalies while taking into account of multivariate nature of the PMU dataset,adapting to concept drift in the flowing PMU data without retraining the existing model unnecessarily and classifying the *** proposed model is implemented in Python and the testing results prove that the proposed model is well suited for detection and classification of anomalies on the fly.