Detecting Anomalous Users via Streaming Data Processing in Smart Grid

Anomalous user detection is an important concern in smart grid. Conduct the anomaly detection in real time with streaming data processing technology is a hot research field for smart grid maintenance. We first study the characteristics of power measurement data. Based on our findings, we adopt Clustream, an outlier detection model, for finding anomalous users. Combined with grid based DBSCAN algorithm, we achieve a two-phase flow processing architecture including offline and online phases for the goal of detecting anomalous user. The implementation details of our system are introduced. The experimental results show that our system can achieve better detection results.

[1]  Alvaro A. Cárdenas,et al.  Evaluating Electricity Theft Detectors in Smart Grid Networks , 2012, RAID.

[2]  Lingfeng Wang,et al.  High performance computing for detection of electricity theft , 2013 .

[3]  Quan Qian,et al.  Grid-based Data Stream Clustering for Intrusion Detection , 2013, Int. J. Netw. Secur..

[4]  Jun Luo,et al.  Energy-theft detection issues for advanced metering infrastructure in smart grid , 2014, Tsinghua Science and Technology.

[5]  Philip S. Yu,et al.  A Framework for Clustering Evolving Data Streams , 2003, VLDB.

[6]  Dai Dong.  Effective Clustering Algorithm for Probabilistic Data Stream , 2009 .

[7]  Lingfeng Wang,et al.  A hybrid neural network model and encoding technique for enhanced classification of energy consumption data , 2011, 2011 IEEE Power and Energy Society General Meeting.

[8]  Won Suk Lee,et al.  Statistical grid-based clustering over data streams , 2004, SGMD.

[9]  Lingfeng Wang,et al.  Support vector machine based data classification for detection of electricity theft , 2011, 2011 IEEE/PES Power Systems Conference and Exposition.

[10]  Aoying Zhou,et al.  Density-Based Clustering over an Evolving Data Stream with Noise , 2006, SDM.

[11]  Sieh Kiong Tiong,et al.  Nontechnical Loss Detection for Metered Customers in Power Utility Using Support Vector Machines , 2010, IEEE Transactions on Power Delivery.

[12]  Alicia Fernández,et al.  Improving Electric Fraud Detection using Class Imbalance Strategies , 2012, ICPRAM.

[13]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[14]  Pan Li,et al.  State estimation for energy theft detection in microgrids , 2014, 9th International Conference on Communications and Networking in China.

[15]  Abhisek Ukil,et al.  Automated analysis of power systems disturbance records: Smart Grid big data perspective , 2014, 2014 IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA).

[16]  Li Tu,et al.  Density-based clustering for real-time stream data , 2007, KDD '07.

[17]  S. Shankar Sastry,et al.  A game theory model for electricity theft detection and privacy-aware control in AMI systems , 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[18]  Gang Zhao,et al.  Effective Clustering Algorithm for Probabilistic Data Stream: Effective Clustering Algorithm for Probabilistic Data Stream , 2010 .