Moving Target Defense Strategy to Protect a PV/Wind Lab-Scale Microgrid Against False Data Injection Cyberattacks: Experimental Validation

This paper proposes a moving target defense (MTD) mechanism in order to protect smart microgrids by decreasing the vulnerability of such systems against false data injection (FDI) cyberattacks. By utilizing the proposed MTD, cyberattackers targeting voltage/current sensors in smart microgrids are limited in their success. The first step of the proposed mechanism involves making multiple copies of the relevant signals (e.g., voltage, current, etc.). The optimal number of copies is obtained by taking into account the number of available sensors and the dynamics of the physical system. Afterwards, only a small number of copies are randomly selected for transmission of their content (i.e., sensor readings). As a final step, the transmitted signals are compared to reference values generated by a recurrent neural network (RNN) in order to verify their validity. The proposed framework is experimentally validated on a lab-scale microgrid, developed in Southern Illinois University, Carbondale, IL, USA, that contains photovoltaic (PV) panels, wind turbines, storage systems, inverters, etc. The entire case study is set up as a hardware-in-the-loop (HIL) testbed utilizing OP4510 real-time digital simulator to handle the experiments.