Statistical Structure Learning to Ensure Data Integrity in Smart Grid

Abstract

Robust control and management of the grid relies on accurate data. Both phasor measurement units and remote terminal units are prone to false data injection attacks. Thus, it is crucial to have a mechanism for fast and accurate detection of tampered data—both for preventing attacks that may lead to blackouts, and for routine monitoring and control of current and future grids. We propose a decentralized false data injection detection scheme based on the Markov graph of the bus phase angles. We utilize the conditional covariance test CMIT to learn the structure of the grid. Using the dc power flow model, we show that, under normal circumstances, the Markov graph of the voltage angles is consistent with the power grid graph. Therefore, a discrepancy between the calculated Markov graph and learned structure should trigger the alarm. Our method can detect the most recent stealthy deception attack on the power grid that assumes knowledge of the bus-branch model of the system and is capable of deceiving the state estimator; hence damaging power network control, monitoring, demand response, and pricing scheme. Specifically, under the stealthy deception attack, the Markov graph of phase angles changes. In addition to detecting a state of attack, our method can detect the set of attacked nodes. To the best of our knowledge, our remedy is the first to comprehensively detect this sophisticated attack and it does not need additional hardware. Moreover, it is successful no matter the size of the attacked subset. Simulation of various power networks confirms our claims.