Catching Anomalous Distributed Photovoltaics: An Edge-based Multi-modal Anomaly Detection

A significant challenge in energy system cyber security is the current inability to detect cyber-physical attacks targeting and originating from distributed grid-edge devices such as photovoltaics (PV) panels, smart flexible loads, and electric vehicles. We address this concern by designing and developing a distributed, multi-modal anomaly detection approach that can sense the health of the device and the electric power grid from the edge. This is realized by exploiting unsupervised machine learning algorithms on multiple sources of time-series data, fusing these multiple local observations and flagging anomalies when a deviation from the normal behavior is observed. We particularly focus on the cyber-physical threats to the distributed PVs that has the potential to cause local disturbances or grid instabilities by creating supply-demand mismatch, reverse power flow conditions etc. We use an open source power system simulation tool called GridLAB-D, loaded with real smart home and solar datasets to simulate the smart grid scenarios and to illustrate the impact of PV attacks on the power system. Various attacks targeting PV panels that create voltage fluctuations, reverse power flow etc were designed and performed. We observe that while individual unsupervised learning algorithms such as OCSVMs, Corrupt RF and PCA surpasses in identifying particular attack type, PCA with Convex Hull outperforms all algorithms in identifying all designed attacks with a true positive rate of 83.64% and an accuracy of 95.78%. Our key insight is that due to the heterogeneous nature of the distribution grid and the uncertainty in the type of the attack being launched, relying on single mode of information for defense can lead to increased false alarms and missed detection rates as one can design attacks to hide within those uncertainties and remain stealthy.

[1]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Yilu Liu,et al.  Power system event location analysis using wide-area measurements , 2006, 2006 IEEE Power Engineering Society General Meeting.

[4]  Valentin Tudor,et al.  Remote Control of Smart Meters: Friend or Foe? , 2011, 2011 Seventh European Conference on Computer Network Defense.

[5]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[6]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[7]  Jeannie R. Albrecht,et al.  Smart * : An Open Data Set and Tools for Enabling Research in Sustainable Homes , 2012 .

[8]  K. M. Muttaqi,et al.  A Novel Approach for Ramp-Rate Control of Solar PV Using Energy Storage to Mitigate Output Fluctuations Caused by Cloud Passing , 2014, IEEE Transactions on Energy Conversion.

[9]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[10]  Melike Erol-Kantarci,et al.  Cyber Attack Protection for a Resilient Electric Vehicle Infrastructure , 2015, 2015 IEEE Globecom Workshops (GC Wkshps).

[11]  Deepa Kundur,et al.  Denial of service attacks and mitigation for stability in cyber-enabled power grid , 2015, 2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[12]  Tobias Heß,et al.  Studies on provision of ancillary services by distributed generation units and storage devices , 2016, 2016 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[13]  Yang Liu,et al.  Leveraging Strategic Detection Techniques for Smart Home Pricing Cyberattacks , 2016, IEEE Transactions on Dependable and Secure Computing.

[14]  Hamed Mohsenian Rad,et al.  Dynamic load altering attacks in smart grid , 2015, 2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[15]  Thomas S. Huang,et al.  One-class SVM for learning in image retrieval , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[16]  Prashant J. Shenoy,et al.  SunSpot: Exposing the Location of Anonymous Solar-powered Homes , 2016, BuildSys@SenSys.

[17]  Chao Liu,et al.  Root-cause analysis for time-series anomalies via spatiotemporal causal graphical modeling , 2016, ArXiv.

[18]  K. Schneider,et al.  GridLAB-D: An open-source power systems modeling and simulation environment , 2008, 2008 IEEE/PES Transmission and Distribution Conference and Exposition.