Towards Energy-Proportional Anomaly Detection in the Smart Grid

Phasor Measurement Unit (PMU) deployment is increasing throughout national power grids in an effort to improve operator situational awareness of rapid oscillations and other fluctuations that could indicate a future disruption of service. However, the quantity of data produced by PMU deployment makes real-time analysis extremely challenging, causing grid designers to invest in large centralized analysis systems that consume significant amounts of energy. In this paper, we argue for a more energy-proportional approach to anomaly detection, and advocate for a decentralized, heterogeneous architecture to keep computational load at acceptable levels for lower-energy chipsets. Our results demonstrate how anomalies can be detected at real-time speeds using single board computers for on-line analysis, and in minutes when running off-line historical analysis using a multicore server running Apache Spark.

[1]  Michael Collins,et al.  Smart grid testbed for Wide-Area Monitoring and Control systems , 2016, 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D).

[2]  Yifeng Zhu,et al.  Design of Hadoop-based Framework for Analytics of Large Synchrophasor Datasets , 2012, Complex Adaptive Systems.

[3]  Bradford Nichols,et al.  Pthreads programming - a POSIX standard for better multiprocessing , 1996 .

[4]  Justin Talbot,et al.  Phoenix++: modular MapReduce for shared-memory systems , 2011, MapReduce '11.

[5]  Vaibhav Fanibhare,et al.  SmartGrids: MapReduce framework using Hadoop , 2016, 2016 3rd International Conference on Signal Processing and Integrated Networks (SPIN).

[6]  Moreno,et al.  ARM+FPGA platform to manage solid-state-smart transformer in smart grid application , 2016, 2016 International Conference on ReConFigurable Computing and FPGAs (ReConFig).

[7]  Suzanne J. Matthews,et al.  Leveraging MapReduce and Synchrophasors for Real-Time Anomaly Detection in the Smart Grid , 2019, IEEE Transactions on Emerging Topics in Computing.

[8]  Uwe G. Kühnapfel,et al.  Power Grid Time Series Data Analysis with Pig on a Hadoop Cluster Compared to Multi Core Systems , 2013, 2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing.

[9]  Ye Zhang,et al.  Distributed Data Analytics Platform for Wide-Area Synchrophasor Measurement Systems , 2016, IEEE Transactions on Smart Grid.

[10]  John James,et al.  Smart grid modeling approach for wide area control applications , 2012, 2012 IEEE Power and Energy Society General Meeting.

[11]  S. A. Mussa,et al.  Three-phase frequency estimator in smart grid applications: Practical issues using FPGA , 2017, 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE).

[12]  Paul Trachian.  Machine learning and windowed subsecond event detection on PMU data via Hadoop and the openPDC , 2010, IEEE PES General Meeting.

[13]  Yong Liu,et al.  Wide-area measurement data analytics using FNET/GridEye: A review , 2016, 2016 Power Systems Computation Conference (PSCC).

[14]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[15]  Li Miao,et al.  The strategy of the voltage control in smart grid based on modern control method and FPGA , 2015, 2015 34th Chinese Control Conference (CCC).

[16]  Luiz André Barroso,et al.  The Case for Energy-Proportional Computing , 2007, Computer.

[17]  Suzanne J. Matthews,et al.  Investigating a Raspberry Pi cluster for detecting anomalies in the smart grid , 2017, 2017 IEEE MIT Undergraduate Research Technology Conference (URTC).

[18]  Junyong Liu,et al.  Parallel Detrended Fluctuation Analysis for Fast Event Detection on Massive PMU Data , 2015, IEEE Transactions on Smart Grid.

[19]  Anna Scaglione,et al.  A Real-Time Testbed Environment for Cyber-Physical Security on the Power Grid , 2015, CPS-SPC@CCS.

[20]  Yilu Liu,et al.  Recent developments of FNET/GridEye — A situational awareness tool for smart grid , 2016 .

[21]  L. Dagum,et al.  OpenMP: an industry standard API for shared-memory programming , 1998 .

[22]  Suzanne J. Matthews,et al.  Leveraging single board computers for anomaly detection in the smart grid , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[23]  Tom White,et al.  Hadoop: The Definitive Guide , 2009 .

[24]  Yong Liu,et al.  Wide-area measurement system development at the distribution level: An FNET/GridEye example , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[25]  Sidharth Rajagopalan,et al.  Synchrophasors Across Texas: The Deployment of Phasor Measurement Technology in the ERCOT Region , 2015, IEEE Power and Energy Magazine.