Merit Logo Merit IconSet
Skip to content

Integrated Smart Grid Analytics for Anomaly Detection

Integrated Smart Grid Analytics for Anomaly Detection

The overarching objective of the modernized electric grid, the smart grid, is to integrate two-way communication technologies across power generation, transmission and distribution to deliver electricity efficiently, securely and cost- effectively. However, real-time messaging exposes the entire grid to security threats ranging from attacks that disable information exchange between smart meters and data fusion centers to spurious payload content that would lead to incorrect assessment of actual demand. Such nefarious activities can compromise grid stability and efficiency. Hence, it is important to ensure secure communications and quickly detect malicious activity; this project aims for accurate and quick detection of false data injection attacks in smart grids.

The main goal of this project is the quick detection of malicious activities that can compromise critical infrastructure, such as the smart power grid. Our methodology to deal with the threat of false data injection attacks is based on correlative monitoring in both home-area networks and also the wide-area setting. For example, in a home-area setting we envision a measurement-based situation awareness framework that can combine evidence from sensors deployed in the house, and aim to infer anomalies that signify a coordinated, well-orchestrated attack on residential smart meters at increasing spatial scales. By leveraging multi-view sensor readings such as temperature, motion, power utilization at individual home circuits, etc., our correlative monitoring approach can quickly detect when power shifts to anomalous regimes.

This project also includes a transition-to-practice component. The main effort there will be to engineer a proof-of-concept implementation of a system for home-area health monitoring and detection of bad data attacks. In particular, we are working on deploying our algorithms to inexpensive computing nodes (such as Raspberry Pi’s) that use off-the-shelf sensors to realize our correlative-based identification mechanism. In partnership with NextEnergy, we plan to evaluate our methods in their NextHome environment. We are also working with University of Michigan Utilities and Plant Engineering for access on real-world power data in various spatio-temporal scales. We envision a cloud-based secure environment that one can utilize to study smart-grid wide-area operations in a realistic manner.

This project is funded by the National Science Foundation (NSF) under the Secure and Trustworthy Cyberspace (SaTC) program.

Recent Publications:

Adaptive Statistical Detection of False Data Injection Attacks in Smart Grids
M. G. Kallitsis, S. Bhattacharya, S. A. Stoev, and G. Michailidis, published at the 2016 IEEE Global Conference on Signal and Information Processing, Washington, DC, December 2016

Correlative Monitoring for Detection of False Data Injection Attacks in Smart Grids (presentation)
Michael Kallitsis, George Michailidis and Samir Tout, to appear in IEEE SmartGridComm 2015, Miami, Florida, November 2015.

A Toolset for Home-area Network Monitoring (Github repo.)
Adrian Padin, Yeabsera Kebede, Max Morgan, Davis Vorva, Michael Kallitsis.

Project Partners: University of Michigan, University of Florida, Eastern Michigan University, NextEnergy